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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14036
    Prev
    Next
    INDEX
    Explanations

    words related to chemicals, biology, and scientific study

    oai_token-act-pair · gemini-2.0-flash

    glu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     Cæsar
    -0.71
    Skor
    -0.68
    ISupport
    -0.68
    WebElementEntity
    -0.65
    kloped
    -0.65
     Monfieur
    -0.63
     Christo
    -0.63
    IContainer
    -0.62
    ftagPool
    -0.62
    windowFixed
    -0.61
    POSITIVE LOGITS
    glBegin
    0.47
     fan
    0.37
     j
    0.36
    jores
    0.36
     הז
    0.36
     mass
    0.36
     J
    0.35
     JOptionPane
    0.35
    DataSetChanged
    0.35
     Mass
    0.35
    Activations Density 1.945%

    No Known Activations