© 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. 20-CLT-HP
    7. 76597
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · 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
    parsedMessage
    -0.84
    __":
    -0.84
    GEBURTSDATUM
    -0.83
    Portály
    -0.82
    MetaObject
    -0.81
     ویکی‌پدی
    -0.81
    __":
    -0.77
    __':
    -0.77
     الرياضيه
    -0.75
    __':
    -0.74
    POSITIVE LOGITS
    บู
    0.43
     jScrollPane
    0.43
     DialogInterface
    0.43
     fu
    0.41
    je
    0.39
     بيها
    0.37
     fuel
    0.36
     extend
    0.34
    usepackage
    0.34
    hu
    0.34
    Activations Density 0.003%

    No Known Activations