© 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. 0-CLT-HP
    7. 44044
    Prev
    Next
    INDEX
    Explanations

    won

    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
     won
    -2.72
    won
    -2.20
    Won
    -2.05
     Won
    -1.88
     WON
    -1.66
    WON
    -1.45
     wont
    -1.35
     winning
    -1.28
     remporté
    -1.19
     gewann
    -1.07
    POSITIVE LOGITS
    ########.
    0.74
     '-';
    0.68
    تقاوى
    0.67
     Савезне
    0.66
    ian
    0.65
     ujednoznacz
    0.64
    CppMethod
    0.63
    OGND
    0.63
    setVerticalGroup
    0.63
     contextLoads
    0.61
    Activations Density 0.023%

    No Known Activations