© 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. 92720
    Prev
    Next
    INDEX
    Explanations

    Code/logs/technical documents

    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
     slik
    -0.49
    ТС
    -0.40
    <bos>
    -0.39
    ();)
    -0.38
    once
    -0.38
    مشخص
    -0.38
    '}),
    -0.37
     أما
    -0.37
    postmedia
    -0.36
    Nicely
    -0.35
    POSITIVE LOGITS
     للاسماء
    0.75
     InputDecoration
    0.73
    IntoConstraints
    0.71
    fjspx
    0.71
     مرئيه
    0.67
    rrggbb
    0.63
     CreateTagHelper
    0.61
     فريبيس
    0.61
    yntaxException
    0.60
     BorderRadius
    0.57
    Activations Density 0.007%

    No Known Activations