© 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. 91852
    Prev
    Next
    INDEX
    Explanations

    team

    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
     \%$\\
    -0.71
    ...");
    -0.70
     ***!
    -0.69
     للمعارف
    -0.69
    <eos>
    -0.67
     يتيمه
    -0.67
    ...');
    -0.67
    }$.\\
    -0.66
     ModelExpression
    -0.65
    yntaxException
    -0.65
    POSITIVE LOGITS
     hiburan
    0.56
     gyhoeddwyd
    0.55
     started
    0.55
     opened
    0.50
     auto
    0.50
    året
    0.49
     tournament
    0.49
    utebol
    0.48
     eight
    0.48
    diğini
    0.48
    Activations Density 0.001%

    No Known Activations