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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11054
    Prev
    Next
    INDEX
    Explanations

    mentions of siblings and family relations, especially older and younger brothers

    oai_token-act-pair · gemini-2.0-flash

    familial relationships, specifically siblings

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

    family members

    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
     AssemblyCulture
    -0.79
    تفصیلات
    -0.60
     ouders
    -0.58
     ApiException
    -0.58
    OOTDTY
    -0.55
     NSCoder
    -0.55
    女儿
    -0.55
    nodoc
    -0.54
    🏻‍♀️
    -0.52
    IVAS
    -0.52
    POSITIVE LOGITS
     brother
    1.44
     Brother
    1.30
     brothers
    1.27
     sister
    1.23
    Brother
    1.22
    brother
    1.21
     bro
    1.19
     younger
    1.18
     sibling
    1.16
     BROTHER
    1.16
    Activations Density 0.838%

    No Known Activations