© 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. 77628
    Prev
    Next
    INDEX
    Explanations

    technical document excerpts

    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
     fifties
    -0.65
    5
    -0.60
    DoubleQuotes
    -0.57
     half
    -0.57
     Fifty
    -0.57
     fifth
    -0.56
     ModelExpression
    -0.56
     FIFTH
    -0.55
     Half
    -0.54
    PerformLayout
    -0.54
    POSITIVE LOGITS
     Infórmanos
    0.56
    utsches
    0.56
     Nin
    0.53
    amerikanischer
    0.52
     Ninth
    0.51
     triple
    0.50
     /\.
    0.49
     '{@
    0.49
    غرب
    0.49
    ANZE
    0.47
    Activations Density 0.000%

    No Known Activations