© 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 · 73079 ｜ Neuronpedia

Home
Gemma-2-2B
20-CLT-HP
73079

INDEX

Explanations

No Explanations Found

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

 فريبيس

-0.65

ussis

-0.58

__*/

-0.55

ఊ

-0.55

 pinning

-0.54

 Gunter

-0.53

 Pinto

-0.53

MigrationBuilder

-0.53

 Latham

-0.52

 straightened

-0.52

POSITIVE LOGITS

Manbalar

0.58

0.58

BeginInit

0.54

0.52

0.50

 Reve

0.50

zur

0.50

Rev

0.49

RE

0.48

REB

0.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.