© 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. 4-CLT-HP
    7. 2268
    Prev
    Next
    INDEX
    Explanations

    open

    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
    ness
    -0.91
    ly
    -0.78
    NESS
    -0.77
    ings
    -0.73
     estekak
    -0.69
     Side
    -0.68
     Meksiku
    -0.68
    selves
    -0.66
     Sign
    -0.66
     Sources
    -0.65
    POSITIVE LOGITS
     CreateTagHelper
    0.47
     initWithFrame
    0.44
     a
    0.44
    ClientSize
    0.39
    zupeł
    0.38
     Améli
    0.37
     Wikidata
    0.37
     the
    0.37
    گاب
    0.37
    SaveChangesAsync
    0.36
    Activations Density 0.001%

    No Known Activations