© 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. 94301
    Prev
    Next
    INDEX
    Explanations

    indefinite articles

    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
     يتيمه
    -0.96
    \{\\
    -0.77
    Искәрмәләр
    -0.76
    LookAnd
    -0.73
    TagMode
    -0.73
     Мексичка
    -0.69
     مشين
    -0.68
    DoubleQuotes
    -0.68
     invokingState
    -0.65
    AddTagHelper
    -0.65
    POSITIVE LOGITS
     different
    0.68
    islative
    0.54
    different
    0.52
     különböző
    0.48
     Different
    0.47
    PreferredItem
    0.47
     good
    0.47
     buena
    0.44
     gewisse
    0.43
     Usaha
    0.43
    Activations Density 0.003%

    No Known Activations