© 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. 4-CLT-HP
    7. 3464
    Prev
    Next
    INDEX
    Explanations

    Formal writing

    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
    ExtendWith
    -0.61
     varandra
    -0.48
     vanligt
    -0.47
    affected
    -0.47
     kvinna
    -0.45
    writing
    -0.45
     skolan
    -0.44
     männis
    -0.44
    lady
    -0.44
     zwar
    -0.44
    POSITIVE LOGITS
    <bos>
    0.69
    AntiForgeryToken
    0.59
    AsUp
    0.57
    saraba
    0.57
    setVerticalGroup
    0.55
     propOrder
    0.54
     unknownFields
    0.54
     eventdata
    0.54
    UnsafeEnabled
    0.53
    httphttps
    0.53
    Activations Density 0.011%

    No Known Activations