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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 2021
    Prev
    Next
    INDEX
    Explanations

    visible

    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
    Visible
    -1.04
     Visible
    -0.98
    visible
    -0.97
     visible
    -0.94
    Vis
    -0.78
    Visibility
    -0.77
    visibility
    -0.73
    s
    -0.69
     visibles
    -0.68
     visually
    -0.66
    POSITIVE LOGITS
    VIAF
    0.82
    Parcelize
    0.77
    featureID
    0.75
    MethodManager
    0.74
    Portale
    0.71
    UserScript
    0.68
    SourceChecksum
    0.67
    ViewImports
    0.67
    UrlResolution
    0.66
    BeginContext
    0.65
    Activations Density 0.140%

    No Known Activations