Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91490
    Prev
    Next
    INDEX
    Explanations

    sick

    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
     sick
    -0.87
     ProtoMessage
    -0.83
     jokes
    -0.75
     laughs
    -0.74
     Sick
    -0.74
     launch
    -0.72
     Laugh
    -0.70
     Jokes
    -0.68
     Efq
    -0.68
     laugh
    -0.67
    POSITIVE LOGITS
    ed
    0.77
    room
    0.55
     ujednoznacz
    0.55
    rooms
    0.54
    ers
    0.53
    ier
    0.52
    ian
    0.52
    s
    0.51
    ifier
    0.49
    atories
    0.49
    Activations Density 0.068%

    No Known Activations