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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15860
    Prev
    Next
    INDEX
    Explanations

    pain

    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
     GenerationType
    -0.77
    endphp
    -0.75
    rawDesc
    -0.73
    RunAsync
    -0.63
    Personensuche
    -0.62
     للمعارف
    -0.61
    writeFieldEnd
    -0.61
     BoxFit
    -0.60
     >=",
    -0.60
    modb
    -0.60
    POSITIVE LOGITS
    makers
    0.52
    UserScript
    0.50
    breaker
    0.48
    fis
    0.48
    Nets
    0.48
    jes
    0.46
    UNIQUE
    0.46
    maker
    0.46
    als
    0.45
    pigeon
    0.45
    Activations Density 0.016%

    No Known Activations