© 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. 40313
    Prev
    Next
    INDEX
    Explanations

    names/file paths

    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
    Taylor
    -0.70
    Bill
    -0.69
     Bill
    -0.63
    AYLOR
    -0.59
    rides
    -0.56
     Taylor
    -0.56
     BILL
    -0.54
    src
    -0.53
    s
    -0.53
     taylor
    -0.52
    POSITIVE LOGITS
     Roskov
    0.71
    AndEndTag
    0.70
     protoimpl
    0.65
    NameInMap
    0.59
    expandindo
    0.57
    IndentedString
    0.57
    Хьажоргаш
    0.56
     Paglinawan
    0.56
     unknownFields
    0.56
    ‌ای
    0.54
    Activations Density 0.047%

    No Known Activations