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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 2123
    Prev
    Next
    INDEX
    Explanations

    the phrase "come to" or "comes to"

    oai_token-act-pair · gemini-2.0-flash

    coming to conclusion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    InjectMocks
    -0.50
    unsplash
    -0.47
     Kinh
    -0.46
    adpleegd
    -0.43
     onPause
    -0.43
    inol
    -0.42
    емся
    -0.42
    haway
    -0.42
    cosh
    -0.42
     令
    -0.41
    POSITIVE LOGITS
    PerformLayout
    0.60
    UnsafeEnabled
    0.59
    >`;
    0.58
     MessageBoxIcon
    0.58
     Administrativna
    0.58
    GEBURTSDATUM
    0.57
    ]}"
    0.56
    Ӕ
    0.56
    )++;
    0.56
    //};
    0.55
    Activations Density 0.777%

    No Known Activations