© 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. 43301
    Prev
    Next
    INDEX
    Explanations

    surprisingly

    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
    principalTable
    -0.77
     Paglinawan
    -0.77
    TestingModule
    -0.73
     itſelf
    -0.68
    elemField
    -0.68
    parsedMessage
    -0.67
     nahilalakip
    -0.66
    cyklopedia
    -0.66
    IntoConstraints
    -0.65
    epiece
    -0.65
    POSITIVE LOGITS
     every
    0.47
     inc
    0.45
    Conception
    0.45
    AllowAnonymous
    0.45
    s
    0.44
     ac
    0.44
    sv
    0.44
     everybody
    0.43
     Stuhl
    0.42
     station
    0.42
    Activations Density 0.066%

    No Known Activations