© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 0-CLT-HP · 41728 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
41728

INDEX

Explanations

onomic

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

 propOrder

-1.23

PDR

-1.21

Efq

-1.15

 Friar

-1.13

 Monfieur

-1.13

NUMX

-1.03

 Theſe

-1.00

 myſelf

-1.00

PDR

-0.99

 purpoſe

-0.97

POSITIVE LOGITS

↵↵

0.56

of

0.54

er

0.53

th

0.53

0.53

0.52

0.51

thal

0.50

la

0.50

0.49

Activations Density 0.114%

No Known Activations