© 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. 9991
    Prev
    Next
    INDEX
    Explanations

    Lists/Enumerated items

    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
    </em>
    -0.60
    </strong>
    -0.46
    M
    -0.46
    AF
    -0.45
    ...
    -0.44
    dimos
    -0.44
     deberes
    -0.44
    /
    -0.43
    AspNetCore
    -0.43
    J
    -0.43
    POSITIVE LOGITS
     ornith
    0.81
     ſche
    0.77
     myſelf
    0.77
     itſelf
    0.76
     xenia
    0.75
     sherds
    0.73
     houſe
    0.72
     fowls
    0.72
     oocytes
    0.71
     geese
    0.71
    Activations Density 0.013%

    No Known Activations