© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12285
    Prev
    Next
    INDEX
    Explanations

    grid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grid
    -1.84
    Grid
    -1.73
     grid
    -1.67
    grid
    -1.63
     GRID
    -1.47
     grids
    -1.38
    GRID
    -1.32
    grids
    -1.03
    GridData
    -0.71
    agrid
    -0.67
    POSITIVE LOGITS
    BagLayout
    0.61
    s
    0.56
     voyons
    0.54
     élevées
    0.54
    checs
    0.54
     générations
    0.52
     élevés
    0.51
     réparer
    0.50
    MENAFN
    0.50
     colpa
    0.50
    Activations Density 0.261%

    No Known Activations