© 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 · 0-CLT-HP · 40994 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
40994

INDEX

Explanations

animals

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

 disambiguazione

-1.26

 يتيمه

-0.94

ReusableCell

-0.94

Personensuche

-0.91

thâu

-0.90

ArgsConstructor

-0.88

出版年

-0.83

ImageContext

-0.83

 فريبيس

-0.82

PMailer

-0.82

POSITIVE LOGITS

0.56

↵

0.56

↵↵

0.52

<eos>

0.49

0.49

0.48

str

0.47

sp

0.46

0.46

life

0.45

Activations Density 0.752%

No Known Activations