© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93617
    Prev
    Next
    INDEX
    Explanations

    Legal/patent documents

    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
    PutMapping
    -0.56
    дравству
    -0.50
     Kirby
    -0.48
    وصلات
    -0.48
     Paglinawan
    -0.48
    ByteBuf
    -0.45
    blogspot
    -0.44
    uyasha
    -0.44
    ctx
    -0.43
     للتو
    -0.43
    POSITIVE LOGITS
    EndInit
    0.74
     otomatig
    0.55
     Discre
    0.54
     Payable
    0.53
     <",
    0.53
     Dryer
    0.52
    addCriterion
    0.50
    principalTable
    0.50
     RESOLUTION
    0.50
    Ecotoxicity
    0.50
    Activations Density 0.037%

    No Known Activations