© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97514
    Prev
    Next
    INDEX
    Explanations

    Russian

    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
     CreateTagHelper
    -0.70
    expandindo
    -0.66
     ExecuteAsync
    -0.61
    parsedMessage
    -0.60
     beginnetje
    -0.60
    DoubleQuotes
    -0.57
    dropIfExists
    -0.52
    TintMode
    -0.52
    ThroughAttribute
    -0.52
    ArgumentParser
    -0.51
    POSITIVE LOGITS
     of
    0.53
    Eksterne
    0.51
    hintText
    0.51
    Revenir
    0.48
    ństw
    0.47
     NSCoder
    0.47
     BorderRadius
    0.46
    })()
    0.46
    brica
    0.45
     precede
    0.44
    Activations Density 0.001%

    No Known Activations