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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16195
    Prev
    Next
    INDEX
    Explanations

    food preparation

    np_max-act-logits · gemini-2.0-flash

    terms related to cooking and food preparation.

    oai_token-act-pair · gemini-2.0-flash

    I am sorry, but I cannot discern any clear pattern in neuron 4's activations. My best guess is: bootstrapcdn

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     yarar
    -0.43
    thar
    -0.41
     maquilla
    -0.39
    TintMode
    -0.38
    ADVERTISEMENT
    -0.38
     ISNI
    -0.38
    ViewFeatures
    -0.38
    ImmutableList
    -0.37
    uple
    -0.37
    offsetTop
    -0.36
    POSITIVE LOGITS
    bootstrapcdn
    0.81
     الاطلاع
    0.65
    InjectAttribute
    0.63
     مرئيه
    0.63
    tonsoft
    0.63
    WriteAttribute
    0.62
    findpost
    0.60
     ویکی‌پدیا
    0.60
    writerow
    0.60
    rawtypes
    0.59
    Activations Density 1.653%

    No Known Activations