© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2604
    Prev
    Next
    INDEX
    Explanations

    Starting new topics

    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
     متعلقه
    -0.94
     مشين
    -0.91
     AssemblyCulture
    -0.84
    parsedMessage
    -0.75
    +#+#
    -0.74
     typelib
    -0.73
     ExecuteAsync
    -0.73
    躇
    -0.68
     <>",
    -0.68
     estekak
    -0.68
    POSITIVE LOGITS
     further
    0.58
     can
    0.52
    며
    0.50
     by
    0.49
     могут
    0.48
     bylaws
    0.48
     stop
    0.48
     realize
    0.48
     don
    0.48
     apologize
    0.47
    Activations Density 0.002%

    No Known Activations