© 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. 91393
    Prev
    Next
    INDEX
    Explanations

    conformation

    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
     humain
    -0.45
    مان
    -0.45
    XMLSchema
    -0.40
     us
    -0.39
    printLine
    -0.39
    NewUrlParser
    -0.39
     voluntarios
    -0.38
    brot
    -0.37
    livet
    -0.37
    complishments
    -0.36
    POSITIVE LOGITS
     فريبيس
    0.95
     صوتيه
    0.75
     }}"></
    0.73
    :✨
    0.68
     Normdatei
    0.67
     NUKAT
    0.66
    protoc
    0.63
    ators
    0.63
     استنادى
    0.63
     protoimpl
    0.62
    Activations Density 0.003%

    No Known Activations