© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1106
    Prev
    Next
    INDEX
    Explanations

    word "world"

    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
     World
    -0.56
    World
    -0.54
    world
    -0.52
     world
    -0.48
     svě
    -0.47
    rc
    -0.44
    “
    -0.43
    it
    -0.43
    pl
    -0.43
    p
    -0.42
    POSITIVE LOGITS
    __*/
    0.85
     AssemblyCompany
    0.84
     الحره
    0.82
     дописавши
    0.81
    AddTagHelper
    0.79
    ynchronously
    0.79
     AssemblyVersion
    0.79
     الاطلاع
    0.76
    تقاوى
    0.74
    parsedMessage
    0.73
    Activations Density 0.132%

    No Known Activations