© 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. 0-CLT-HP
    7. 45299
    Prev
    Next
    INDEX
    Explanations

    General, outlet

    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
     outlet
    -0.81
    General
    -0.73
     Outlet
    -0.60
    r
    -0.58
    Y
    -0.58
    p
    -0.56
    er
    -0.56
     Outlets
    -0.56
    l
    -0.56
    y
    -0.55
    POSITIVE LOGITS
    IUrlHelper
    0.87
    StructEnd
    0.80
    OGND
    0.79
    >");
    0.78
     &___
    0.77
    '):
    0.77
    Климат
    0.75
    LookAnd
    0.74
    SourceChecksum
    0.74
    BibitemShut
    0.72
    Activations Density 0.172%

    No Known Activations