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. 16172
    Prev
    Next
    INDEX
    Explanations

    technical language about CPU cooling

    oai_token-act-pair · gemini-2.0-flash

    heatpipes

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

    product descriptions

    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
     المعيارى
    -0.77
    GraphicsUnit
    -0.76
    Vidite
    -0.75
     ProtoMessage
    -0.74
     pinulongan
    -0.74
    HtmlAttribute
    -0.74
     sumpay
    -0.73
     дописавши
    -0.73
     SwitchCompat
    -0.73
    trường
    -0.71
    POSITIVE LOGITS
    title
    0.41
    getTitle
    0.40
     Pic
    0.40
    Associated
    0.39
     Associated
    0.39
    ಾದ
    0.39
     voeding
    0.39
     Title
    0.38
     chia
    0.38
    게
    0.38
    Activations Density 2.842%

    No Known Activations