© 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. 1-CLT-HP
    7. 15745
    Prev
    Next
    INDEX
    Explanations

    sulfur

    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
     }}"></
    -0.67
    Autoritní
    -0.56
     OMIT
    -0.54
     rotund
    -0.52
    oczes
    -0.51
    ifiquement
    -0.50
    ритори
    -0.50
    cunt
    -0.50
    isers
    -0.50
    SharedCtor
    -0.50
    POSITIVE LOGITS
    twimg
    0.60
     StatelessWidget
    0.59
     ivelany
    0.58
    providedIn
    0.57
     NSCoder
    0.55
     StatefulWidget
    0.52
     Brigade
    0.52
     Helm
    0.50
    Helm
    0.47
    Getenv
    0.47
    Activations Density 0.156%

    No Known Activations