© 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. 4-CLT-HP
    7. 2928
    Prev
    Next
    INDEX
    Explanations

    child

    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
     ArrayAdapter
    -0.47
     estekak
    -0.46
     فريبيس
    -0.44
     المعيارى
    -0.44
    MessageInfo
    -0.44
    EqualsAnd
    -0.42
     resultCode
    -0.41
    setMode
    -0.40
    InteropServices
    -0.40
    epam
    -0.39
    POSITIVE LOGITS
    like
    0.71
    bearing
    0.70
    holder
    0.69
    worker
    0.69
    buyer
    0.68
    runner
    0.65
    MigrationBuilder
    0.65
    tiness
    0.64
    let
    0.63
    fighter
    0.63
    Activations Density 0.002%

    No Known Activations