© 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. 0-CLT-HP
    7. 95757
    Prev
    Next
    INDEX
    Explanations

    field

    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
     trouw
    -0.56
     Réponses
    -0.52
    LogFactory
    -0.50
     pensée
    -0.48
    onedDateTime
    -0.47
    WriteTagHelper
    -0.46
    -------------</
    -0.46
     avoient
    -0.46
     Había
    -0.46
     étoient
    -0.45
    POSITIVE LOGITS
    '
    0.73
     wireType
    0.63
    situation
    0.63
     we
    0.63
    AnimationsModule
    0.62
    encodeWith
    0.59
    ’
    0.59
     most
    0.58
    期刊论文
    0.58
    WebServlet
    0.58
    Activations Density 0.116%

    No Known Activations