© 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. 94135
    Prev
    Next
    INDEX
    Explanations

    can

    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
     rasc
    -0.45
    ogenic
    -0.45
    w
    -0.45
     Michoacán
    -0.45
     vaak
    -0.43
     (
    -0.42
     priva
    -0.42
     bastards
    -0.41
    f
    -0.41
    +
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.70
    AndEndTag
    0.68
     HasFactory
    0.67
    LabelTagHelper
    0.63
    SharedDtor
    0.62
     then
    0.62
     even
    0.61
     >=",
    0.61
     resourceCulture
    0.60
     незавершена
    0.60
    Activations Density 0.003%

    No Known Activations