© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38460
    Prev
    Next
    INDEX
    Explanations

    urine

    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
     Grid
    -0.94
    safety
    -0.90
     safety
    -0.87
     urine
    -0.86
     Urine
    -0.86
     grid
    -0.85
    grid
    -0.80
    Grid
    -0.80
     SAFETY
    -0.79
     Safety
    -0.79
    POSITIVE LOGITS
    WebMethod
    0.53
     चीज़ों
    0.49
     listings
    0.47
    HtmlAttribute
    0.46
     viewType
    0.45
    StartTag
    0.43
    BufferException
    0.43
    EndInit
    0.43
     getItemId
    0.42
    Leh
    0.40
    Activations Density 0.089%

    No Known Activations