© 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. 5337
    Prev
    Next
    INDEX
    Explanations

    and/hyphen

    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
     itſelf
    -1.17
     houſe
    -1.03
     purpoſe
    -1.02
     Efq
    -1.02
     ſeveral
    -1.02
     myſelf
    -1.00
     Reſ
    -0.99
     ſmall
    -0.98
     Jefus
    -0.98
     greateſt
    -0.97
    POSITIVE LOGITS
    /
    0.72
    ,
    0.69
     for
    0.68
     /
    0.68
     in
    0.66
     can
    0.63
     will
    0.63
     with
    0.63
     at
    0.63
     to
    0.63
    Activations Density 0.002%

    No Known Activations