© 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. 42576
    Prev
    Next
    INDEX
    Explanations

    sex

    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
    FI
    -0.48
     LA
    -0.47
     ré
    -0.45
    edition
    -0.44
     der
    -0.44
     din
    -0.43
    SHR
    -0.43
     List
    -0.42
    Shannon
    -0.42
    ļa
    -0.42
    POSITIVE LOGITS
     Jefus
    0.88
     purpoſe
    0.82
    ſelf
    0.80
    Vidite
    0.80
     fubject
    0.79
    ſelves
    0.78
     Efq
    0.77
     Reſ
    0.77
     myſelf
    0.77
     ſever
    0.77
    Activations Density 0.387%

    No Known Activations