© 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. 1-CLT-HP
    7. 9853
    Prev
    Next
    INDEX
    Explanations

    radi

    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
    __(/*!
    -0.86
     AssemblyCulture
    -0.83
    TagMode
    -0.82
     resourceCulture
    -0.79
    Datuak
    -0.79
     StatefulWidget
    -0.77
     للمعارف
    -0.75
    IUrlHelper
    -0.75
    DoubleQuotes
    -0.75
     bezeichneter
    -0.74
    POSITIVE LOGITS
    archiviato
    0.45
     sus
    0.43
     Kirchner
    0.42
    GRY
    0.38
    ubel
    0.38
    kano
    0.38
    itorio
    0.37
    destru
    0.37
     une
    0.37
     indisponible
    0.37
    Activations Density 0.031%

    No Known Activations