© 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. 0-CLT-HP
    7. 42791
    Prev
    Next
    INDEX
    Explanations

    water

    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
     water
    -1.70
    water
    -1.31
     Water
    -1.28
    Water
    -1.23
     WATER
    -1.06
    WATER
    -1.02
     vatten
    -1.02
    水
    -0.99
     waters
    -0.95
     água
    -0.92
    POSITIVE LOGITS
    BeginInit
    0.89
     BoxDecoration
    0.85
     كومونز
    0.83
     فريبيس
    0.82
    MemoryWarning
    0.79
    +#+#
    0.77
     ***!
    0.75
    AccessorTable
    0.72
    RectangleBorder
    0.71
    :✨
    0.70
    Activations Density 0.030%

    No Known Activations