© 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. 98272
    Prev
    Next
    INDEX
    Explanations

    result

    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
    marked
    -0.49
    toHaveBeenCalled
    -0.48
    PyExc
    -0.46
     bezeichneter
    -0.45
    UnsafeEnabled
    -0.45
     Spector
    -0.45
     OFDb
    -0.44
    Glej
    -0.44
     用于
    -0.42
    ⮕
    -0.40
    POSITIVE LOGITS
     of
    0.81
    parsedMessage
    0.78
    ValueStyle
    0.61
    FilterChain
    0.58
    iastes
    0.54
     CURIAM
    0.52
    Ecotoxicity
    0.52
     économie
    0.49
    RuleContext
    0.49
    machus
    0.49
    Activations Density 0.001%

    No Known Activations