© 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. 4-CLT-HP
    7. 1698
    Prev
    Next
    INDEX
    Explanations

    antibodies

    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
    AddTagHelper
    -0.73
     kecuali
    -0.67
     excepto
    -0.67
    ทั้งหมด
    -0.65
    Including
    -0.63
     tuturor
    -0.63
     sauf
    -0.62
     всіх
    -0.62
     Wikimedijinoj
    -0.61
     semua
    -0.60
    POSITIVE LOGITS
     समीक्षाएं
    0.73
    APOLIS
    0.69
    VersionUID
    0.56
     QtCore
    0.56
    Nazionale
    0.56
    SourceChecksum
    0.54
     саны
    0.54
    minecraft
    0.54
     Référence
    0.53
    uitable
    0.53
    Activations Density 0.061%

    No Known Activations