© 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. 5-CLT-HP
    7. 6273
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
     population
    -0.55
     and
    -0.46
    vency
    -0.42
     centaines
    -0.41
     Einwilligung
    -0.40
    openhauer
    -0.39
    alt
    -0.38
     average
    -0.38
     or
    -0.36
     e
    -0.35
    POSITIVE LOGITS
    ⓧ
    0.94
    featureID
    0.83
     deſt
    0.78
     consultato
    0.77
    addCriterion
    0.77
    basicConfig
    0.73
    parsedMessage
    0.73
     doubtnut
    0.73
     Wikimedijinoj
    0.73
     Himo
    0.72
    Activations Density 0.010%

    No Known Activations