© 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. 91804
    Prev
    Next
    INDEX
    Explanations

    data analysis

    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
     determine
    -0.59
     determining
    -0.54
     poszczegól
    -0.54
     determines
    -0.54
     specific
    -0.53
     different
    -0.50
    specific
    -0.49
     detailed
    -0.46
     Determining
    -0.46
     actual
    -0.45
    POSITIVE LOGITS
     مرئيه
    0.77
     виправивши
    0.72
    FundMe
    0.68
     ADI
    0.68
    AntiForgeryToken
    0.63
     <>",
    0.63
    Nazionale
    0.62
     Theſe
    0.61
     TextInputType
    0.60
     angler
    0.59
    Activations Density 0.021%

    No Known Activations