© 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. 72462
    Prev
    Next
    INDEX
    Explanations

    Introductory text

    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
    IUrlHelper
    -0.98
    ьаж
    -0.77
    PageContext
    -0.75
     ProtoMessage
    -0.75
    RuleContext
    -0.74
    مصادر
    -0.71
    Хьажоргаш
    -0.71
    contentLoaded
    -0.68
    adaptiveStyles
    -0.68
    CppMethod
    -0.68
    POSITIVE LOGITS
     popular
    0.62
     take
    0.62
     pass
    0.60
     takes
    0.50
    pass
    0.49
    take
    0.49
     pop
    0.49
    passing
    0.49
    popular
    0.48
     Passing
    0.47
    Activations Density 0.000%

    No Known Activations