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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14169
    Prev
    Next
    INDEX
    Explanations

    words relating to academic research and scientific study

    oai_token-act-pair · gemini-2.0-flash

    scientific methods and interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
     recev
    -0.58
     Trailers
    -0.49
    Supers
    -0.48
     Uang
    -0.48
     vậy
    -0.47
     Pró
    -0.46
     Periodicals
    -0.46
     depre
    -0.46
     unworthy
    -0.46
    noaa
    -0.45
    POSITIVE LOGITS
     synergy
    0.92
     synergies
    0.87
     interplay
    0.86
     together
    0.78
    Portail
    0.77
     intertwined
    0.76
     partnership
    0.75
     synergistic
    0.73
     combination
    0.71
     interaction
    0.71
    Activations Density 1.492%

    No Known Activations