© 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. 5-CLT-HP
    7. 97346
    Prev
    Next
    INDEX
    Explanations

    leadership roles

    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
    oa̍t
    -0.73
    bbene
    -0.71
     prisonniers
    -0.71
    ArrowToggle
    -0.70
    FTFY
    -0.69
     fallu
    -0.69
     étoit
    -0.68
     Signalez
    -0.68
     réfugiés
    -0.68
     nôtre
    -0.68
    POSITIVE LOGITS
     at
    0.64
     as
    0.59
     <<<<<<<<<<<<<<
    0.54
    مصادر
    0.52
     over
    0.50
     in
    0.47
     ceremonies
    0.47
    as
    0.46
    é
    0.46
    ed
    0.45
    Activations Density 0.001%

    No Known Activations