© 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. 1-CLT-HP
    7. 12188
    Prev
    Next
    INDEX
    Explanations

    good

    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
     typelib
    -0.61
    devamını
    -0.54
    Portail
    -0.52
     مرئيه
    -0.52
    CloseOperation
    -0.52
    ñoz
    -0.50
    :^(
    -0.49
     ویکی‌پدیا
    -0.48
     defaultstate
    -0.48
    GARET
    -0.46
    POSITIVE LOGITS
     purpoſe
    0.61
     contextLoads
    0.59
    writeFieldEnd
    0.57
     sapiens
    0.53
    ForValue
    0.52
    AntiForgeryToken
    0.52
     }{@
    0.52
     myndig
    0.51
    Hap
    0.51
    ativistic
    0.51
    Activations Density 0.005%

    No Known Activations