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. 20-CLT-HP
    4. 73611
    Prev
    Next
    INDEX
    Explanations

    adverbs of certainty

    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
     AssemblyTitle
    -0.76
     fallu
    -0.64
    ⓧ
    -0.63
    ftagPool
    -0.62
    脚注の使い方
    -0.60
     kautta
    -0.60
     للاسماء
    -0.58
     <>",
    -0.57
     legyen
    -0.56
    adpleegd
    -0.55
    POSITIVE LOGITS
     never
    0.78
     definitely
    0.76
     also
    0.72
     rarely
    0.72
     certainly
    0.69
     always
    0.68
     hardly
    0.66
     struggles
    0.65
     really
    0.65
     still
    0.65
    Activations Density 0.009%

    No Known Activations