© 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. 94173
    Prev
    Next
    INDEX
    Explanations

    volving

    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
    __;
    -0.78
    sizeCache
    -0.77
    afficheront
    -0.73
    fromnode
    -0.68
    queryInterface
    -0.68
    AddField
    -0.68
    complexContent
    -0.68
    ))->
    -0.67
    verifyException
    -0.67
    ItemBackground
    -0.67
    POSITIVE LOGITS
    ing
    0.47
    ana
    0.42
     zd
    0.42
     in
    0.41
    CommandText
    0.41
    ёр
    0.40
    um
    0.40
     sleeper
    0.40
    antes
    0.40
    IsContent
    0.39
    Activations Density 1.630%

    No Known Activations