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. 16351
    Prev
    Next
    INDEX
    Explanations

    sentences about events happening after someone's death

    oai_token-act-pair · gemini-2.0-flash

    death

    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
    HtmlAttribute
    -0.67
    FTFY
    -0.66
    CGRectMake
    -0.63
    ArgsConstructor
    -0.63
    getMinutes
    -0.59
    ichni
    -0.59
     CWE
    -0.57
    yntaxException
    -0.57
    topus
    -0.55
     متحده
    -0.55
    POSITIVE LOGITS
     death
    0.88
    death
    0.75
     retirement
    0.73
    Death
    0.60
     DEATH
    0.59
     graduation
    0.57
    retirement
    0.56
     defeat
    0.54
     Death
    0.54
     injury
    0.53
    Activations Density 1.759%

    No Known Activations