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. 810
    Prev
    Next
    INDEX
    Explanations

    leave/stay

    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
     leave
    -1.00
     Leave
    -0.89
    Leave
    -0.85
     stay
    -0.84
    leave
    -0.81
     Stay
    -0.77
     LEAVE
    -0.76
    Stay
    -0.69
    stay
    -0.58
     STAY
    -0.58
    POSITIVE LOGITS
    orated
    0.58
    ridgeshire
    0.57
     imageNamed
    0.57
     Мексичка
    0.56
     consulté
    0.56
    Trichloroethane
    0.56
     imprisoned
    0.56
    qvarna
    0.56
    NOPQRST
    0.56
    KommentareTeilen
    0.55
    Activations Density 0.037%

    No Known Activations