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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73973
    Prev
    Next
    INDEX
    Explanations

    screen

    np_max-act-logits · 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
     kasarigan
    -0.84
     <>",
    -0.81
    CppCodeGen
    -0.72
    rawDesc
    -0.64
    CROSSTALK
    -0.61
     الدولى
    -0.61
    hésite
    -0.60
    RenderAtEndOf
    -0.58
    AnchorTagHelper
    -0.58
    PhysRevD
    -0.57
    POSITIVE LOGITS
     screened
    0.57
     screening
    0.56
     Screening
    0.55
     Мексичка
    0.54
    screen
    0.51
    creen
    0.51
    Screening
    0.50
    screening
    0.49
     Highly
    0.49
     screenings
    0.48
    Activations Density 0.000%

    No Known Activations