© 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. 1-CLT-HP
    4. 13300
    Prev
    Next
    INDEX
    Explanations

    flat

    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
    +#+#
    -0.70
     חיצוניים
    -0.68
    MLLoader
    -0.66
    TintMode
    -0.60
     Caste
    -0.58
     Mantis
    -0.57
     snippetHide
    -0.57
     Superhost
    -0.56
     Rector
    -0.56
    setVerticalGroup
    -0.55
    POSITIVE LOGITS
    test
    0.52
    bar
    0.50
    斑
    0.48
     spot
    0.46
    spot
    0.46
    found
    0.45
    goto
    0.45
    throw
    0.45
    ARDO
    0.45
    bij
    0.44
    Activations Density 0.096%

    No Known Activations