© 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. 96532
    Prev
    Next
    INDEX
    Explanations

    article

    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
     ath
    -0.57
    FormTagHelper
    -0.57
     grà
    -0.52
    thaler
    -0.50
    ath
    -0.50
     disambiguazione
    -0.49
     thọ
    -0.49
    ATH
    -0.48
    toObject
    -0.47
    TagMode
    -0.47
    POSITIVE LOGITS
    expandindo
    0.68
    ConverterFactory
    0.62
    ViewFeatures
    0.61
    PreExecute
    0.57
     GenerationType
    0.57
    ChildScrollView
    0.56
     isComment
    0.56
     FES
    0.54
     WebDriverWait
    0.54
     insuffisamment
    0.54
    Activations Density 0.001%

    No Known Activations