© 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. 5-CLT-HP
    7. 4990
    Prev
    Next
    INDEX
    Explanations

    causation

    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
    OMB
    -0.53
     indirect
    -0.52
    Closeable
    -0.47
     Armed
    -0.46
     or
    -0.46
     SAU
    -0.45
     Indirect
    -0.45
     Bright
    -0.45
    emp
    -0.45
    šanai
    -0.44
    POSITIVE LOGITS
     lenker
    1.02
    NewGuid
    0.66
    rungsseite
    0.64
    RegressionTest
    0.61
    出版年
    0.60
    قایناق‌لار
    0.59
    lovakia
    0.56
     चीज़ों
    0.55
    :✨
    0.54
     ***!
    0.54
    Activations Density 0.002%

    No Known Activations