© 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 · 91982 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
91982

INDEX

Explanations

past tense verbs

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

 grew

-1.68

 flew

-1.48

 drove

-1.41

 gave

-1.38

grew

-1.37

 drew

-1.35

 wore

-1.33

 blew

-1.30

 withdrew

-1.23

 arose

-1.23

POSITIVE LOGITS

0.82

 taken

0.82

 written

0.77

the

0.76

 done

0.73

 some

0.71

 different

0.69

man

0.68

 those

0.67

 them

0.66

Activations Density 0.049%

No Known Activations