© 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. 4-CLT-HP
    7. 4489
    Prev
    Next
    INDEX
    Explanations

    #

    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
    queryInterface
    -0.73
    Autoritní
    -0.72
    DockStyle
    -0.70
    AndEndTag
    -0.66
     StatefulWidget
    -0.65
     متعلقه
    -0.62
    LikeLiked
    -0.61
     it
    -0.61
    WriteTagHelper
    -0.61
    invokeLater
    -0.60
    POSITIVE LOGITS
     pleaſure
    0.49
    ſelf
    0.47
     geox
    0.47
     fubject
    0.46
     ſta
    0.44
     ſche
    0.44
     myſelf
    0.43
     neceffary
    0.42
     Anſ
    0.41
     poffible
    0.41
    Activations Density 0.000%

    No Known Activations