© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41870
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    recrow
    -1.34
    macher
    -1.30
    DeleteBehavior
    -0.88
     Scarecrow
    -0.78
    DockStyle
    -0.77
     utafitiHapana
    -0.70
    setupUi
    -0.65
     calendriers
    -0.63
    isNotBlank
    -0.62
    initComponents
    -0.60
    POSITIVE LOGITS
    relli
    0.54
    or
    0.50
    on
    0.50
    out
    0.50
     vivent
    0.48
     vivió
    0.47
    hofer
    0.47
    ondis
    0.47
    host
    0.47
    Host
    0.47
    Activations Density 1.339%

    No Known Activations