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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14147
    Prev
    Next
    INDEX
    Explanations

    references to someone's job title of "head" of something

    oai_token-act-pair · gemini-2.0-flash

    head

    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
    Parcelize
    -0.65
    tvguidetime
    -0.61
    menjadi
    -0.55
    ISupport
    -0.54
    ंदीखरीदारी
    -0.53
    ArgumentParser
    -0.52
    ThroughAttribute
    -0.51
     Gub
    -0.51
     فريبيس
    -0.50
    ifié
    -0.50
    POSITIVE LOGITS
     of
    0.51
    ueuse
    0.47
     incomplète
    0.47
    Jereo
    0.47
     beginnetje
    0.47
     inglesa
    0.47
    person
    0.45
     polvere
    0.45
    AddHtmlAttribute
    0.45
     خارجی
    0.45
    Activations Density 0.133%

    No Known Activations