© 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. 93926
    Prev
    Next
    INDEX
    Explanations

    JP

    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
    js
    -0.90
    JP
    -0.85
    JS
    -0.81
     js
    -0.72
    jp
    -0.72
    leading
    -0.59
     JP
    -0.59
     JS
    -0.57
    Js
    -0.52
    antd
    -0.45
    POSITIVE LOGITS
    SequentialGroup
    0.90
    EDEFAULT
    0.84
     שוליים
    0.77
    PerformLayout
    0.75
    )++;
    0.72
    ."));
    0.70
     Efq
    0.70
    parsedMessage
    0.70
    SharedDtor
    0.69
    ContentAsync
    0.69
    Activations Density 0.354%

    No Known Activations