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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10145
    Prev
    Next
    INDEX
    Explanations

    the word "very" and forms of the word incredible

    oai_token-act-pair · gemini-2.0-flash

    Very

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_19/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
    WithMany
    -0.52
    Spoiler
    -0.48
     Contamin
    -0.44
     abstraction
    -0.43
    uegos
    -0.43
     vediamo
    -0.42
    CAPS
    -0.42
     tellement
    -0.41
    λίου
    -0.41
    rayage
    -0.41
    POSITIVE LOGITS
    تقاوى
    0.75
     initComponents
    0.74
     autorytatywna
    0.72
     propOrder
    0.69
     pinulongan
    0.69
     BorderRadius
    0.68
     opérés
    0.65
     AssemblyVersion
    0.64
     fieldNum
    0.60
    ArrowToggle
    0.59
    Activations Density 0.289%

    No Known Activations