© 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. 15984
    Prev
    Next
    INDEX
    Explanations

    weather/storms

    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
    <bos>
    -0.68
    H
    -0.46
     réponses
    -0.40
     Hi
    -0.40
     H
    -0.40
     rate
    -0.39
     poussière
    -0.38
    HideInInspector
    -0.38
    Tracce
    -0.37
    */
    -0.36
    POSITIVE LOGITS
    ValueStyle
    0.96
     &___
    0.93
    ConstraintMaker
    0.84
    VersionUID
    0.79
    WithIOException
    0.75
    enterOuterAlt
    0.73
    routeProvider
    0.71
    CppCodeGen
    0.71
    parsedMessage
    0.71
    boldmath
    0.68
    Activations Density 0.011%

    No Known Activations