© 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. 40608
    Prev
    Next
    INDEX
    Explanations

    able

    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
    able
    -1.33
    ability
    -1.05
    ABLE
    -0.77
    table
    -0.77
    time
    -0.76
    Able
    -0.72
     able
    -0.69
    let
    -0.68
    lets
    -0.66
     quæ
    -0.63
    POSITIVE LOGITS
    ANDUM
    0.62
    DoubleQuotes
    0.61
    dci
    0.60
    InvalidProtocol
    0.59
    PreferredItem
    0.59
     ddelweddau
    0.59
    MLLoader
    0.58
    stonia
    0.58
    contentLoaded
    0.55
    TestingModule
    0.54
    Activations Density 0.385%

    No Known Activations