© 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. 0-CLT-HP
    7. 42239
    Prev
    Next
    INDEX
    Explanations

    frames

    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
    ValueStyle
    -0.87
     propOrder
    -0.82
     savoury
    -0.66
    UnusedPrivate
    -0.66
    GEBURTSDATUM
    -0.65
     AssemblyCulture
    -0.64
    SourceChecksum
    -0.63
    IsPostBack
    -0.62
     ModelExpression
    -0.62
     برانيه
    -0.61
    POSITIVE LOGITS
     Minister
    0.44
    ">+
    0.43
     '%
    0.43
    нъ
    0.43
    casian
    0.42
     minister
    0.42
    ﹍﹍﹍
    0.42
    enegro
    0.41
    ycznego
    0.41
    utscher
    0.41
    Activations Density 0.067%

    No Known Activations