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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74072
    Prev
    Next
    INDEX
    Explanations

    "either"

    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
     both
    -1.03
     Both
    -1.02
    both
    -0.98
    Both
    -0.98
     båda
    -0.95
     begge
    -0.90
     entrambi
    -0.84
     Beide
    -0.83
     beide
    -0.81
     ambas
    -0.79
    POSITIVE LOGITS
     either
    3.02
    either
    2.67
    Either
    2.58
     Either
    2.58
     entweder
    2.34
     enten
    1.66
    要么
    1.60
     либо
    1.24
     soit
    1.14
    ither
    1.09
    Activations Density 0.002%

    No Known Activations