© 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. 91060
    Prev
    Next
    INDEX
    Explanations

    膨胀

    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
    \{\\
    -0.62
    tagHelperRunner
    -0.57
    InSection
    -0.56
    PageFactory
    -0.56
    Zdroje
    -0.54
    зможно
    -0.54
    träd
    -0.51
     SqlCommand
    -0.50
     JAXBElement
    -0.50
     tả
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.57
    ieteur
    0.50
     jsPsych
    0.50
    RTEX
    0.49
    NameInMap
    0.47
    WebServlet
    0.47
    ViewFeatures
    0.47
    はじめに
    0.46
    ophone
    0.45
    charis
    0.45
    Activations Density 0.002%

    No Known Activations