© 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. 94457
    Prev
    Next
    INDEX
    Explanations

    surgical

    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
     Ar
    -0.73
     ar
    -0.68
     AR
    -0.60
    Ar
    -0.59
    ural
    -0.53
     of
    -0.52
    ju
    -0.52
    bir
    -0.51
    otto
    -0.49
     έ
    -0.49
    POSITIVE LOGITS
     Monfieur
    1.16
     Jefus
    1.07
     myſelf
    1.06
     Efq
    0.99
    ſelf
    0.97
     itſelf
    0.94
     Cæsar
    0.93
     ainfi
    0.91
     Majefty
    0.90
     uſed
    0.86
    Activations Density 0.205%

    No Known Activations