© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39926
    Prev
    Next
    INDEX
    Explanations

    in

    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
    GEBURTSDATUM
    -0.95
    Personensuche
    -0.86
    出版年
    -0.81
    Jeografia
    -0.80
    WriteTagHelper
    -0.79
    ImageContext
    -0.79
     ModelExpression
    -0.78
    twimg
    -0.78
     propOrder
    -0.77
     disambiguazione
    -0.76
    POSITIVE LOGITS
     allmän
    0.55
     general
    0.52
    General
    0.45
     General
    0.44
     encontram
    0.43
    general
    0.43
    anmoins
    0.43
     femenino
    0.42
     in
    0.41
    horabuena
    0.41
    Activations Density 0.032%

    No Known Activations