© 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. 2868
    Prev
    Next
    INDEX
    Explanations

    parenthesis

    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
     незавершена
    -0.64
    protoc
    -0.63
    RTSC
    -0.57
     getRule
    -0.55
     виправивши
    -0.55
     noDo
    -0.54
    invokeLater
    -0.53
    횟
    -0.50
    not
    -0.49
    허
    -0.47
    POSITIVE LOGITS
    حياتها
    0.56
    eburger
    0.56
    istus
    0.54
    anadas
    0.53
    ersham
    0.52
    estars
    0.52
    sertations
    0.52
    estries
    0.52
    sumoto
    0.52
    ppuden
    0.51
    Activations Density 0.011%

    No Known Activations