© 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. 15863
    Prev
    Next
    INDEX
    Explanations

    pector

    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
     StatefulWidget
    -0.83
     ostavi
    -0.75
     Gerard
    -0.71
     Theſe
    -0.71
     étoit
    -0.69
    TestingModule
    -0.68
     Meksiku
    -0.67
     avoient
    -0.66
     Shores
    -0.66
    出版年
    -0.65
    POSITIVE LOGITS
    s
    0.52
    CloseOperation
    0.45
    y
    0.43
    t
    0.42
     continue
    0.40
    ాల
    0.39
    bac
    0.39
    d
    0.39
    }></
    0.38
     IndexPath
    0.38
    Activations Density 0.051%

    No Known Activations