© 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. 94715
    Prev
    Next
    INDEX
    Explanations

    mixtures

    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
    -2.08
     Efq
    -1.97
     myſelf
    -1.95
     raiſ
    -1.94
     Eſ
    -1.83
     Jefus
    -1.79
     ſtate
    -1.78
     Reſ
    -1.77
     houſe
    -1.76
     iſt
    -1.75
    POSITIVE LOGITS
    .
    0.85
     in
    0.84
     (
    0.83
     to
    0.77
     
    0.72
     l
    0.71
     on
    0.70
     for
    0.69
     with
    0.69
     M
    0.68
    Activations Density 0.257%

    No Known Activations