© 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. 90891
    Prev
    Next
    INDEX
    Explanations

    history

    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
     goes
    -0.54
    Tại
    -0.54
    MethodManager
    -0.53
     includes
    -0.52
     darin
    -0.51
     calendriers
    -0.48
     departments
    -0.48
    )_/¯
    -0.47
     in
    -0.47
    corollary
    -0.47
    POSITIVE LOGITS
    :✨
    0.76
    ValueStyle
    0.66
    شهاد
    0.64
     @"/
    0.64
    DoubleQuotes
    0.64
     FetchType
    0.63
    sizeCache
    0.60
    NameInMap
    0.59
    Hentet
    0.59
     suggestive
    0.55
    Activations Density 0.005%

    No Known Activations