© 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. 20-CLT-HP
    7. 72635
    Prev
    Next
    INDEX
    Explanations

    Biology and Genetics

    np_max-act-logits · 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
     JpaRepository
    -0.78
     متعلقه
    -0.75
    ANTLR
    -0.71
    EndInit
    -0.71
     незавершена
    -0.69
     الحره
    -0.65
    phrine
    -0.61
    esModule
    -0.61
     AspNetCore
    -0.60
    UnknownFields
    -0.60
    POSITIVE LOGITS
    staa
    0.44
    siao
    0.44
    st
    0.41
     stá
    0.41
    estu
    0.40
    este
    0.38
     Val
    0.38
    WindowConstants
    0.37
    kå
    0.37
    斯坦
    0.37
    Activations Density 0.001%

    No Known Activations