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. 73817
    Prev
    Next
    INDEX
    Explanations

    Code, abbreviations, mixed languages

    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
     noires
    -0.68
     Bantu
    -0.63
     African
    -0.63
     Negroes
    -0.62
     blackness
    -0.60
    raught
    -0.59
     Africans
    -0.59
     black
    -0.59
     BoxFit
    -0.58
     AssemblyCulture
    -0.58
    POSITIVE LOGITS
    :+:
    0.53
    出版年
    0.49
    +#+
    0.49
    :✨
    0.45
     Ch
    0.44
     Lat
    0.44
     Latino
    0.43
    __((
    0.42
     lat
    0.41
     जा
    0.40
    Activations Density 0.005%

    No Known Activations