© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38297
    Prev
    Next
    INDEX
    Explanations

    indicator

    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
     Indicator
    -1.07
     indicator
    -0.90
     indicators
    -0.82
    Indicator
    -0.81
     Indicators
    -0.81
    indicator
    -0.74
    indicators
    -0.73
    Indicators
    -0.70
     indicadores
    -0.65
    INDICATOR
    -0.57
    POSITIVE LOGITS
    +#+#
    0.77
    بوابة
    0.72
     للمعارف
    0.65
    omeness
    0.65
    ChildScrollView
    0.63
     tfsi
    0.63
    marle
    0.63
    AndEndTag
    0.61
    wwwwwwww
    0.61
     Theſe
    0.61
    Activations Density 1.611%

    No Known Activations