© 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. 0-CLT-HP
    7. 38406
    Prev
    Next
    INDEX
    Explanations

    invitation

    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
    uxxxx
    -1.19
     تانيه
    -1.09
    AddTagHelper
    -1.08
    AndEndTag
    -1.00
     محفوظة
    -0.99
     wireType
    -0.98
     ModelExpression
    -0.93
     resourceCulture
    -0.92
    UrlResolution
    -0.91
    ^(@)
    -0.91
    POSITIVE LOGITS
    ing
    0.89
    '
    0.56
    ,
    0.52
    -
    0.51
    .
    0.49
    /
    0.49
    (
    0.49
    ’
    0.47
     (
    0.47
    and
    0.46
    Activations Density 1.675%

    No Known Activations