© 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. 5-CLT-HP
    7. 93255
    Prev
    Next
    INDEX
    Explanations

    of

    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
    цезда
    -0.48
     zä
    -0.44
    继续阅读
    -0.44
     marker
    -0.44
     sonda
    -0.43
     ModelExpression
    -0.43
    racene
    -0.42
     Paglinawan
    -0.42
     sendiri
    -0.42
    :][
    -0.41
    POSITIVE LOGITS
    CloseOperation
    0.77
     rotation
    0.76
     alertness
    0.72
     homogeneity
    0.72
     curvature
    0.69
     clarity
    0.68
     sweetness
    0.67
    ParallelGroup
    0.67
     regularity
    0.67
     smoothness
    0.67
    Activations Density 0.001%

    No Known Activations