© 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. 5-CLT-HP
    7. 91657
    Prev
    Next
    INDEX
    Explanations

    see

    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
     BorderRadius
    -0.65
    complexContent
    -0.59
    uesto
    -0.59
     fVar
    -0.57
     onOptions
    -0.57
    出版年
    -0.57
    DeleteBehavior
    -0.57
    PositiveButton
    -0.57
    nóstico
    -0.56
     äm
    -0.56
    POSITIVE LOGITS
     whether
    0.83
     where
    0.72
     how
    0.70
     what
    0.69
     if
    0.69
     which
    0.56
     a
    0.55
    терак
    0.55
    AntiForgeryToken
    0.52
     '\\;'
    0.52
    Activations Density 0.001%

    No Known Activations