© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16139
    Prev
    Next
    INDEX
    Explanations

    time, money, energy

    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
    Negative Logits
     مشين
    -0.81
    setVerticalGroup
    -0.72
    quelize
    -0.70
    $_['
    -0.69
     AssemblyCulture
    -0.68
    帖最后由
    -0.68
    ]]
    -0.68
    WebVitals
    -0.66
    protoimpl
    -0.66
    enumi
    -0.66
    POSITIVE LOGITS
     for
    0.47
     Wikimedijinoj
    0.46
     to
    0.41
    Preconditions
    0.40
     stolen
    0.40
    лии
    0.38
    apyrus
    0.37
    Luck
    0.36
    brania
    0.35
     diretto
    0.35
    Activations Density 0.020%

    No Known Activations