© 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. 9764
    Prev
    Next
    INDEX
    Explanations

    9, 0

    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
    AttributeSet
    -0.56
    unhofer
    -0.42
     parseFrom
    -0.38
    testify
    -0.38
    unmodifiable
    -0.36
     bask
    -0.36
    じる
    -0.35
     ↑
    -0.35
    Rè
    -0.35
     dut
    -0.35
    POSITIVE LOGITS
     nawr
    0.75
    UserScript
    0.73
    новниш
    0.70
    MLLoader
    0.69
    ArrowToggle
    0.69
     للاسماء
    0.69
     purpoſe
    0.68
    ंदीखरीदारी
    0.68
     nôtre
    0.65
    Personensuche
    0.65
    Activations Density 0.325%

    No Known Activations