© 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. 0-CLT-HP
    7. 90493
    Prev
    Next
    INDEX
    Explanations

    {

    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
    belec
    -0.54
    bootstrapcdn
    -0.49
    zewod
    -0.48
    ãs
    -0.47
     onOptions
    -0.47
    ValueGeneration
    -0.47
    幻
    -0.46
    Kanpo
    -0.46
    íslu
    -0.46
     Independ
    -0.46
    POSITIVE LOGITS
    FunctionFlags
    0.77
    (!__
    0.68
    OwnProperty
    0.65
    CppMethod
    0.61
     offside
    0.61
    InstrumentedTest
    0.59
    -------------</
    0.58
     تضيفلها
    0.57
    itados
    0.57
    mobileqq
    0.56
    Activations Density 0.460%

    No Known Activations