© 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. 94156
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    Autoritní
    -0.60
     ď
    -0.52
     Hiv
    -0.50
     RAB
    -0.49
     Kä
    -0.49
    ampunk
    -0.48
    Сред
    -0.48
     Median
    -0.48
    arrant
    -0.47
     Pohl
    -0.47
    POSITIVE LOGITS
    aarrggbb
    0.93
    TagMode
    0.72
    AndEndTag
    0.69
     تضيفلها
    0.65
     متعلقه
    0.63
     MainAxisSize
    0.62
    IsMutable
    0.57
    AsUp
    0.56
    RenderAtEndOf
    0.56
    Portály
    0.56
    Activations Density 0.783%

    No Known Activations