Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16367
    Prev
    Next
    INDEX
    Explanations

    LaTeX symbols and equations

    oai_token-act-pair · gemini-2.0-flash

    mathematical formulas

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

    bracket

    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
    tvguidetime
    -0.60
     виправивши
    -0.59
    InputBorder
    -0.57
     kasarigan
    -0.55
    kalk
    -0.54
    WriteTagHelper
    -0.50
     SAU
    -0.49
    uali
    -0.49
    }}{{
    -0.49
     amp
    -0.48
    POSITIVE LOGITS
     amitié
    0.69
     gyhoeddwyd
    0.58
     rêver
    0.56
     légère
    0.54
     écoute
    0.53
     Ressources
    0.53
     ProtoMessage
    0.53
     pitié
    0.52
     écout
    0.52
     debout
    0.51
    Activations Density 2.393%

    No Known Activations