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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14305
    Prev
    Next
    INDEX
    Explanations

    the word "nature"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nature
    -3.09
    nature
    -2.66
    Nature
    -2.44
     Nature
    -2.44
     NATURE
    -2.28
     naturaleza
    -1.91
     natureza
    -1.91
    NATURE
    -1.71
     natures
    -1.68
     natura
    -1.45
    POSITIVE LOGITS
    abestanden
    0.75
    QMetaType
    0.73
     وتسجيلات
    0.73
    }])
    0.72
    )";
    
    0.71
     stället
    0.71
    "])
    
    0.71
    )++;
    0.70
    '}),
    0.69
    "];
    
    0.68
    Activations Density 0.254%

    No Known Activations