© 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. 1-CLT-HP
    7. 9788
    Prev
    Next
    INDEX
    Explanations

    import

    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
    IsRequired
    -0.54
     Du
    -0.49
    <eos>
    -0.49
    hy
    -0.49
     Her
    -0.48
     Hy
    -0.47
     D
    -0.47
     by
    -0.46
    ↵↵
    -0.46
     al
    -0.46
    POSITIVE LOGITS
     Jefus
    1.02
     purpoſe
    1.01
     myſelf
    1.00
     ſmall
    0.98
     pleaſure
    0.95
     uſed
    0.94
     faſt
    0.92
     houſe
    0.92
     cauſe
    0.92
     raiſ
    0.91
    Activations Density 6.629%

    No Known Activations