© 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 · 0-CLT-HP · 39830 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
39830

INDEX

Explanations

Norwegian

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

 Theſe

-1.02

 pleaſure

-1.02

ſelf

-1.01

CppMethod

-0.96

 ſche

-0.95

 itſelf

-0.95

 Jefus

-0.92

 Norway

-0.91

ſelves

-0.90

fulness

-0.90

POSITIVE LOGITS

is

0.53

in

0.51

0.46

0.46

0.44

0.43

tud

0.42

ProgressHUD

0.41

er

0.41

::_('

0.41

Activations Density 0.075%

No Known Activations