© 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. 94098
    Prev
    Next
    INDEX
    Explanations

    proto

    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
     lion
    -0.68
     Lion
    -0.58
    Hentet
    -0.57
     dégust
    -0.56
    :+:
    -0.54
     Chicken
    -0.54
    zbęd
    -0.54
     réve
    -0.53
     lions
    -0.52
     TextAppearance
    -0.52
    POSITIVE LOGITS
    ized
    0.56
    ization
    0.56
    hilt
    0.55
     Klon
    0.53
    berry
    0.52
     idio
    0.51
    ipedia
    0.50
    NSNotification
    0.50
    ViewChild
    0.50
     tears
    0.50
    Activations Density 0.143%

    No Known Activations