© 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. 4-CLT-HP
    7. 823
    Prev
    Next
    INDEX
    Explanations

    Minister

    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
    OGND
    -0.63
     Letra
    -0.52
    colhead
    -0.50
    SaveChangesAsync
    -0.48
    CDATA
    -0.44
    脚注の使い方
    -0.44
    სქოლიო
    -0.43
    Rcpp
    -0.43
     OSI
    -0.42
     letra
    -0.42
    POSITIVE LOGITS
     for
    0.79
    MLLoader
    0.69
     Without
    0.66
    errHandler
    0.65
     AssemblyCulture
    0.63
     without
    0.63
    ial
    0.61
    ftagPool
    0.59
    without
    0.58
     für
    0.57
    Activations Density 0.011%

    No Known Activations