© 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. 3009
    Prev
    Next
    INDEX
    Explanations

    document snippets

    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
     
    -0.52
     or
    -0.44
    datalist
    -0.42
     now
    -0.42
     between
    -0.40
     وسلم
    -0.40
    نجليز
    -0.39
     $
    -0.39
    chon
    -0.39
     Ne
    -0.37
    POSITIVE LOGITS
    IUrlHelper
    0.80
    Abitanti
    0.79
     Efq
    0.77
     مرئيه
    0.75
     Chriftian
    0.71
     Monfieur
    0.69
     Houſe
    0.68
     poffe
    0.68
     raiſ
    0.68
     otomatig
    0.67
    Activations Density 0.003%

    No Known Activations