© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

GEMMA-2-2B · 5-CLT-HP · 94671 ｜ Neuronpedia

Home
Gemma-2-2B
5-CLT-HP
94671

INDEX

Explanations

Arm

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

al

-0.53

EndTag

-0.47

opsida

-0.46

vo

-0.46

Personensuche

-0.45

fromnode

-0.44

-0.44

-0.43

Rüyada

-0.43

-0.42

POSITIVE LOGITS

 مشين

0.65

THINK

0.57

Efq

0.56

AndEndTag

0.56

 Sporting

0.55

spesies

0.54

 fubject

0.53

 earthen

0.53

 ſmall

0.53

 Pente

0.52

Activations Density 0.001%

No Known Activations