© 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 · 0-CLT-HP · 95371 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
95371

INDEX

Explanations

point

np_max-act · 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

 point

-1.56

 Point

-1.17

point

-1.16

 POINT

-1.03

Point

-1.00

 punto

-0.97

 points

-0.82

 Points

-0.78

POINT

-0.78

点

-0.78

POSITIVE LOGITS

subpackage

0.54

 toim

0.50

 nascita

0.50

าย

0.48

zęd

0.47

ḏ

0.47

 hornear

0.46

सन्दर्भ

0.44

 setia

0.44

 régler

0.44

Activations Density 0.054%

No Known Activations