© 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. 20-CLT-HP
    7. 76651
    Prev
    Next
    INDEX
    Explanations

    people

    np_max-act-logits · 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
    aarrggbb
    -0.84
     nakalista
    -0.78
    DockStyle
    -0.65
    Diweddarwch
    -0.65
    RectangleBorder
    -0.62
    awtextra
    -0.61
    +#+#
    -0.61
    brews
    -0.57
    TagMode
    -0.56
     Disqus
    -0.56
    POSITIVE LOGITS
     c
    0.57
     cru
    0.50
     hu
    0.49
    witz
    0.48
    /_
    0.48
     gu
    0.47
     Dafür
    0.45
    翘
    0.45
     shop
    0.43
    peed
    0.42
    Activations Density 0.000%

    No Known Activations