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. 5881
    Prev
    Next
    INDEX
    Explanations

    words that add emphasis or positivity to the main subject

    oai_token-act-pair · gemini-2.0-flash

    terms related to sources and references

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

    sources

    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
     AssemblyTitle
    -0.58
     &___
    -0.57
    GEBURTSDATUM
    -0.49
    RTLR
    -0.49
    idosis
    -0.47
    oso
    -0.47
     استنادى
    -0.46
    ContentAsync
    -0.46
    Risultati
    -0.45
    ServiceModel
    -0.45
    POSITIVE LOGITS
     fonte
    0.80
     fuente
    0.79
     sources
    0.77
     source
    0.76
     degré
    0.75
    "]);
    
    0.72
    sources
    0.72
     Sources
    0.69
     degree
    0.69
    areas
    0.68
    Activations Density 2.131%

    No Known Activations