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. 2111
    Prev
    Next
    INDEX
    Explanations

    references to age, particularly of people.

    oai_token-act-pair · gemini-2.0-flash

    age

    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
     age
    -2.22
     aged
    -2.06
     ages
    -1.88
     Age
    -1.81
    Age
    -1.73
     Aged
    -1.71
    Aged
    -1.63
    aged
    -1.63
     AGE
    -1.55
    age
    -1.51
    POSITIVE LOGITS
     مرئيه
    0.88
    новниш
    0.63
     Italijanski
    0.56
    niająca
    0.55
    فایل‌لار
    0.51
    XmlAccessType
    0.50
     BoxFit
    0.49
    arka
    0.49
     JUGA
    0.49
    FieldBuilder
    0.47
    Activations Density 0.305%

    No Known Activations