© 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. 14483
    Prev
    Next
    INDEX
    Explanations

    dashes

    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
    uf
    -0.46
    رشف
    -0.42
    mu
    -0.42
     Mu
    -0.42
    ,
    -0.42
     Hooper
    -0.41
    :
    -0.40
    Mu
    -0.40
     Mer
    -0.40
     kvad
    -0.39
    POSITIVE LOGITS
    tonode
    0.76
     disambiguazione
    0.75
    IndentedString
    0.73
     /\.
    0.70
    RetentionPolicy
    0.69
    \{\\
    0.68
     }}"></
    0.68
     /\.(
    0.66
    NUMX
    0.66
    RectangleBorder
    0.65
    Activations Density 0.023%

    No Known Activations