© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-2-2B · 5-CLT-HP · 2004 ｜ Neuronpedia

Home
Gemma-2-2B
5-CLT-HP
2004

INDEX

Explanations

feasibility

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

 Monfieur

-0.94

 myſelf

-0.93

Efq

-0.92

HtmlAttribute

-0.88

 itſelf

-0.87

ſelf

-0.86

 whoſe

-0.84

 houſe

-0.84

 iſt

-0.83

 Jefus

-0.78

POSITIVE LOGITS

0.58

fır

0.46

0.42

0.41

gebirge

0.40

 nacimiento

0.40

0.40

DeleteMapping

0.40

my

0.40

0.38

Activations Density 0.000%

No Known Activations