NCA-GENL Data Analysis and Visualization Practice Question
A data scientist is preparing an exploratory report on a large corpus of prompt-completion pairs used to fine-tune an LLM. They want to visualize the distribution of a single numerical feature, prompt token count, to check for skew before choosing a tokenization budget. Which visualization is most appropriate?
⚠ Common exam trap
The trap here is reaching for an embedding projection when the task only requires understanding one numerical variable's distribution.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
A histogram of prompt token counts.
When the goal is to inspect the shape of one continuous variable, a histogram is the natural choice. It reveals skew, gaps, and multiple peaks in prompt token counts, which directly informs how large a tokenization budget should be. Other charts either summarize relationships or display categories, not univariate distribution shape.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A stacked bar chart of prompt categories by split.
Why it's wrong here
A stacked bar chart compares categorical composition across groups, not the distribution of a continuous variable. It cannot reveal skew in prompt token counts and would misrepresent a numerical feature as categories, so it does not support the tokenization budget decision.
- ✗
A t-SNE scatter plot of prompt embeddings.
Why it's wrong here
A t-SNE plot projects high-dimensional embeddings into two dimensions for cluster inspection. It does not display the univariate distribution of prompt token counts and its axes are not interpretable as token counts, so it is the wrong tool for this univariate skew check.
- ✓
A histogram of prompt token counts.
Why this is correct
A histogram bins a single numerical variable and reveals its shape, including skew and possible multimodality. For prompt token counts, that directly informs the tokenization budget by showing where most prompts fall and how far the tail extends.
- ✗
A correlation heatmap of all numerical features.
Why it's wrong here
A correlation heatmap summarizes pairwise linear relationships between many features, not the shape of one distribution. It would not show whether prompt token counts are skewed or where the mass of the distribution lies, so it cannot guide the tokenization budget decision.
About these practice questions
Courseiva writes every NCA-GENL question from scratch — 367 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official NVIDIA exam blueprint
This NCA-GENL practice question is part of Courseiva's free NVIDIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the NCA-GENL exam.