© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1114
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     république
    -0.72
    queles
    -0.71
     démocratie
    -0.70
     amitié
    -0.69
     souffrance
    -0.69
     bonté
    -0.68
     paroisse
    -0.68
     vícti
    -0.66
     humeur
    -0.66
    withstanding
    -0.66
    POSITIVE LOGITS
    DeleteBehavior
    0.62
     sum
    0.57
     lot
    0.56
     day
    0.55
     list
    0.54
     gli
    0.52
     bra
    0.50
     familiar
    0.50
     table
    0.50
    mergeFrom
    0.50
    Activations Density 0.832%

    No Known Activations