© 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. 43273
    Prev
    Next
    INDEX
    Explanations

    also

    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
     Theſe
    -1.57
    Also
    -1.51
     itſelf
    -1.47
     Also
    -1.42
     Monfieur
    -1.30
     Diſ
    -1.29
     Majefty
    -1.28
     alſo
    -1.27
     Efq
    -1.26
     auffi
    -1.25
    POSITIVE LOGITS
    ,
    0.97
     had
    0.90
     a
    0.89
     made
    0.86
     an
    0.85
     has
    0.83
     known
    0.78
     have
    0.77
     the
    0.76
     in
    0.76
    Activations Density 0.037%

    No Known Activations