© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97471
    Prev
    Next
    INDEX
    Explanations

    cell

    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
     précie
    -0.66
    ORETICAL
    -0.65
     كومونز
    -0.65
    vgili
    -0.65
     näm
    -0.65
     EconPapers
    -0.63
    tiérrez
    -0.61
    nemies
    -0.60
     vœux
    -0.60
    pingente
    -0.60
    POSITIVE LOGITS
    ActionCreators
    0.59
    var
    0.53
    **
    0.52
    ida
    0.50
    <b>
    0.48
    '
    0.48
    saraba
    0.48
    URLException
    0.47
    *
    0.46
    <h1>
    0.46
    Activations Density 0.062%

    No Known Activations