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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39908
    Prev
    Next
    INDEX
    Explanations

    lunch

    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
     lunch
    -1.08
     lunchtime
    -1.05
     pomeriggio
    -1.00
     evening
    -0.98
     mediodía
    -0.96
    lunch
    -0.95
     florales
    -0.94
     kvä
    -0.93
     prochaines
    -0.92
     stället
    -0.91
    POSITIVE LOGITS
    ing
    0.87
    ed
    0.60
    ING
    0.57
    ette
    0.57
    ers
    0.55
    etts
    0.53
    y
    0.53
    PickerController
    0.52
     te
    0.52
    es
    0.50
    Activations Density 0.081%

    No Known Activations