© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9375
    Prev
    Next
    INDEX
    Explanations

    den

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ModelAdmin
    -0.57
    SuccessListener
    -0.50
     Wikimedijinoj
    -0.49
    Soorten
    -0.47
     VIDEOTAPE
    -0.47
     FontFamily
    -0.47
    calipsis
    -0.47
    setVerticalGroup
    -0.47
    StructEnd
    -0.46
    ppins
    -0.46
    POSITIVE LOGITS
    featureID
    0.59
     năng
    0.56
     RoutedEventArgs
    0.51
    itive
    0.50
    permum
    0.48
     оригіналу
    0.48
     happiest
    0.47
    esia
    0.47
    arean
    0.47
    heide
    0.46
    Activations Density 0.046%

    No Known Activations