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. 16174
    Prev
    Next
    INDEX
    Explanations

    programming code question fragments

    oai_token-act-pair · gemini-2.0-flash

    and it

    np_token-act-pair-logits · gemini-2.0-flash

    sentence/clause continuation

    np_max-act-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
     solche
    -0.51
    ButtonModule
    -0.49
    isable
    -0.49
    mmation
    -0.48
    EndInit
    -0.47
    Such
    -0.45
     such
    -0.45
    waite
    -0.43
     Tut
    -0.43
     Such
    -0.42
    POSITIVE LOGITS
     it
    1.16
     they
    0.79
     оно
    0.77
    它
    0.76
    ГЛА
    0.75
    XmlAccessType
    0.73
     дописавши
    0.72
     חיצוניים
    0.71
    它是
    0.71
     שוליים
    0.71
    Activations Density 2.603%

    No Known Activations