© 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. 2252
    Prev
    Next
    INDEX
    Explanations

    it

    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
    AccessorTable
    -0.93
    LookAnd
    -0.84
     NSCoder
    -0.77
    RTEX
    -0.77
     дописавши
    -0.77
    RetentionPolicy
    -0.76
    parsedMessage
    -0.76
     ProtoMessage
    -0.76
     propOrder
    -0.75
    SharedDtor
    -0.75
    POSITIVE LOGITS
     تانيه
    0.51
     semula
    0.50
     voraus
    0.46
    例文帳に追加
    0.45
     earlier
    0.44
     florales
    0.44
    ATURE
    0.44
    ailleurs
    0.43
     modernos
    0.43
    earlier
    0.42
    Activations Density 0.002%

    No Known Activations