© 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. 0-CLT-HP
    7. 93431
    Prev
    Next
    INDEX
    Explanations

    updating

    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
     update
    -1.34
     evolution
    -1.24
     evolve
    -1.20
    update
    -1.13
     évolution
    -1.12
     Update
    -1.09
     updates
    -1.09
     evolves
    -1.09
     evolución
    -1.08
     updating
    -1.06
    POSITIVE LOGITS
     StatefulWidget
    0.68
    al
    0.67
     assuming
    0.63
     RoutedEventArgs
    0.61
     pageContext
    0.60
     Asparagus
    0.55
     XCTest
    0.54
    енча
    0.54
     nastro
    0.54
    Hozzáférés
    0.51
    Activations Density 0.098%

    No Known Activations