© 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. 43101
    Prev
    Next
    INDEX
    Explanations

    SP

    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
     
    -1.19
     P
    -0.94
     a
    -0.92
     SP
    -0.89
     the
    -0.89
     in
    -0.88
     (
    -0.87
    ,
    -0.86
     A
    -0.85
     I
    -0.84
    POSITIVE LOGITS
     Efq
    2.38
     itſelf
    2.33
     myſelf
    2.27
     Monfieur
    2.11
     themſelves
    2.03
     Reſ
    2.03
     raiſ
    2.02
     Houſe
    2.02
     himſelf
    1.99
     Anſ
    1.99
    Activations Density 0.946%

    No Known Activations