© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 20-CLT-HP · 75795 ｜ Neuronpedia

Home
Gemma-2-2B
20-CLT-HP
75795

INDEX

Explanations

letter "A"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.72

findpost

-0.66

AsUp

-0.65

 aikaa

-0.63

 typelib

-0.61

исленность

-0.59

ⓘ

-0.59

CP

-0.57

OGND

-0.56

kloped

-0.56

POSITIVE LOGITS

0.64

0.58

0.57

例句

0.51

Ａ

0.46

 مشين

0.45

iii

0.42

localctx

0.40

 aden

0.40

antd

0.40

Activations Density 0.001%

No Known Activations