© 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. 9439
    Prev
    Next
    INDEX
    Explanations

    duct

    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
     duct
    -0.73
     Duct
    -0.69
     ducts
    -0.63
    duct
    -0.54
    elect
    -0.49
    ducts
    -0.46
    extraction
    -0.45
     varandra
    -0.45
    elections
    -0.43
    eyes
    -0.42
    POSITIVE LOGITS
     EconPapers
    0.60
    mybatisplus
    0.60
     SqlDbType
    0.57
     الرياضيه
    0.57
    RegressionTest
    0.56
    ות
    0.56
    us
    0.56
    ServletException
    0.56
    al
    0.54
    CompleteListener
    0.54
    Activations Density 0.007%

    No Known Activations