© 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. 5104
    Prev
    Next
    INDEX
    Explanations

    code, addresses, descriptions

    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
    梭
    -0.41
    E
    -0.40
    ıyordu
    -0.38
    jek
    -0.38
     consultative
    -0.37
    popularity
    -0.37
     possibili
    -0.37
    Sh
    -0.37
     Sh
    -0.36
    गी
    -0.36
    POSITIVE LOGITS
    CppMethod
    0.85
    таратура
    0.79
     [*]
    0.76
    featureID
    0.71
    aarrggbb
    0.70
    DotNetBar
    0.69
     للمعارف
    0.68
    atimes
    0.66
     חיצוניים
    0.65
     resourceCulture
    0.65
    Activations Density 0.004%

    No Known Activations