© 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. 0-CLT-HP
    7. 41718
    Prev
    Next
    INDEX
    Explanations

    SPECIFIC

    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
    Particular
    -0.67
     Particular
    -0.60
    particular
    -0.55
    i
    -0.50
     fact
    -0.50
     particular
    -0.49
     Kombat
    -0.48
    TypedDataSet
    -0.48
    ی
    -0.46
     individual
    -0.45
    POSITIVE LOGITS
     समीक्षाओं
    0.68
    persons
    0.65
    aways
    0.65
     *>(
    0.65
     chi̍t
    0.64
     للاسماء
    0.63
    NameInMap
    0.61
     Italijani
    0.61
     <=",
    0.61
     Paglinawan
    0.61
    Activations Density 0.052%

    No Known Activations