© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95002
    Prev
    Next
    INDEX
    Explanations

    leisure

    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
    ORIAL
    -0.88
    thal
    -0.85
     leisure
    -0.85
    orial
    -0.84
    leisure
    -0.73
     Leisure
    -0.69
     autorytatywna
    -0.68
    новништво
    -0.66
    Leisure
    -0.65
     élas
    -0.63
    POSITIVE LOGITS
    y
    0.62
    s
    0.58
    e
    0.57
    otry
    0.52
     sympathies
    0.50
    merkungen
    0.50
    staat
    0.50
    BackPressed
    0.48
    プーン
    0.48
    tikzpicture
    0.48
    Activations Density 0.367%

    No Known Activations