© 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. 5-CLT-HP
    7. 1977
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
    ApplicationTests
    -0.52
     Réponses
    -0.51
    tonsoft
    -0.48
    ArrowToggle
    -0.48
    unica
    -0.48
    __).
    -0.47
    رشف
    -0.47
    RTLU
    -0.46
    shall
    -0.46
    acaktır
    -0.45
    POSITIVE LOGITS
     word
    0.66
    Hozzáférés
    0.62
     talk
    0.61
    ГЛА
    0.56
     palabra
    0.56
     TALK
    0.56
     BoxDecoration
    0.55
     referring
    0.53
     CreateTagHelper
    0.53
     mention
    0.52
    Activations Density 0.006%

    No Known Activations