© 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. 42424
    Prev
    Next
    INDEX
    Explanations

    under

    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
    ,
    -0.94
     in
    -0.89
    .
    -0.85
     under
    -0.77
     of
    -0.76
    g
    -0.69
     (
    -0.68
    -
    -0.65
     on
    -0.62
    ;
    -0.61
    POSITIVE LOGITS
     Efq
    1.39
     myſelf
    1.36
    NUMX
    1.30
     purpoſe
    1.30
     photolibrary
    1.28
     itſelf
    1.28
     Jefus
    1.27
    extAlignment
    1.26
     ſmall
    1.25
     greateſt
    1.25
    Activations Density 0.113%

    No Known Activations