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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5859
    Prev
    Next
    INDEX
    Explanations

    names

    oai_token-act-pair · gemini-2.0-flash

    words and tokens related to names

    np_token-act-pair-logits · gpt-4o-mini

    Names in email headers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     Theſe
    -1.15
     houſe
    -0.98
     Monfieur
    -0.97
     ſche
    -0.97
     Reſ
    -0.96
     pleaſure
    -0.95
     Houſe
    -0.94
     purpoſe
    -0.91
     Anſ
    -0.90
     ſtate
    -0.90
    POSITIVE LOGITS
    ficult
    0.71
    ')));
    0.63
     D
    0.59
    ficulty
    0.59
    ")));
    
    0.59
    ReadKey
    0.58
     N
    0.57
    tificates
    0.56
    isielt
    0.55
    ]$}
    0.54
    Activations Density 4.404%

    No Known Activations