© 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. 94498
    Prev
    Next
    INDEX
    Explanations

    places

    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
    -1.90
     myſelf
    -1.87
     Anſ
    -1.84
     Monfieur
    -1.80
     ―――――
    -1.70
     Reſ
    -1.69
     doubtnut
    -1.67
     Shakspeare
    -1.66
     Theſe
    -1.65
     Efq
    -1.64
    POSITIVE LOGITS
     (
    0.95
     a
    0.93
     
    0.88
     the
    0.86
     in
    0.86
     A
    0.83
    <eos>
    0.82
     G
    0.81
    ,
    0.79
     S
    0.77
    Activations Density 0.328%

    No Known Activations