© 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. 5-CLT-HP
    7. 97219
    Prev
    Next
    INDEX
    Explanations

    including

    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
    PreferredItem
    -0.74
     kaarangay
    -0.74
    BeginInit
    -0.73
     незавершена
    -0.72
     للاسماء
    -0.71
     respectively
    -0.71
     respectivamente
    -0.69
    onViewCreated
    -0.67
    ViewFeatures
    -0.67
    RegressionTest
    -0.67
    POSITIVE LOGITS
    inguém
    0.49
     mungkin
    0.48
    liwości
    0.46
     Internet
    0.45
     of
    0.44
     U
    0.42
    nyk
    0.42
    queryInterface
    0.42
     Zu
    0.42
     
    0.42
    Activations Density 0.013%

    No Known Activations