© 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. 20-CLT-HP
    7. 77079
    Prev
    Next
    INDEX
    Explanations

    Code and technical text

    np_max-act-logits · 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
    ukone
    -0.63
    COUVER
    -0.56
    __":
    -0.53
    EMU
    -0.50
     imp
    -0.50
    الدراسه
    -0.49
    سطس
    -0.49
    Datuak
    -0.49
    zzleHttp
    -0.48
    #!/
    -0.48
    POSITIVE LOGITS
    jsxFileName
    0.50
     Filed
    0.50
    millimeters
    0.47
    OutputType
    0.47
    őle
    0.46
    fili
    0.46
    百里
    0.46
    InvalidProtocol
    0.46
     VizieR
    0.46
    awtextra
    0.46
    Activations Density 0.000%

    No Known Activations