© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14253
    Prev
    Next
    INDEX
    Explanations

    astronomy, physics

    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
    <bos>
    -0.64
     nahilalakip
    -0.49
    RenderAtEndOf
    -0.48
    QMetaType
    -0.47
    getch
    -0.47
    autoreleasepool
    -0.47
     BoxFit
    -0.46
     mxArray
    -0.46
    colgroup
    -0.46
    __':
    -0.46
    POSITIVE LOGITS
     виправивши
    0.60
    Personensuche
    0.56
     Alden
    0.54
     للاسماء
    0.52
    ModelAdmin
    0.51
    πισ
    0.51
     Bumi
    0.51
     APS
    0.51
     oprot
    0.50
    ijen
    0.50
    Activations Density 0.039%

    No Known Activations