© 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 · 20-CLT-HP · 74768 ｜ Neuronpedia

Home
Gemma-2-2B
20-CLT-HP
74768

INDEX

Explanations

animals

np_max-act-logits · 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

aries

-0.50

ients

-0.49

vity

-0.46

als

-0.44

ρω

-0.44

 kasarigan

-0.43

 JFrame

-0.43

teht

-0.43

vux

-0.41

oves

-0.41

POSITIVE LOGITS

girl

0.75

catcher

0.70

prince

0.69

hunter

0.69

herd

0.68

child

0.67

boy

0.66

god

0.64

whisper

0.64

man

0.63

Activations Density 0.007%

No Known Activations