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. 5898
    Prev
    Next
    INDEX
    Explanations

    text about cemeteries and death

    oai_token-act-pair · gemini-2.0-flash

    terms related to cemeteries

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

    cemeteries and burials

    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
     auxquelles
    -0.46
     tangga
    -0.45
    ném
    -0.42
     hồi
    -0.42
    찍
    -0.41
     való
    -0.41
     Zon
    -0.41
     zaten
    -0.40
    Wyd
    -0.40
     betale
    -0.40
    POSITIVE LOGITS
    TestingModule
    0.79
    GEBURTSDATUM
    0.72
     &___
    0.67
    NameInMap
    0.66
     nakalista
    0.65
    Newswire
    0.64
    PhysRevD
    0.64
     समीक्षाओं
    0.63
     استنادى
    0.63
     }}$}
    0.63
    Activations Density 0.211%

    No Known Activations