© 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. 5-CLT-HP
    7. 696
    Prev
    Next
    INDEX
    Explanations

    Copying information/Code snippets

    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
    ToBounds
    -0.57
     dAtA
    -0.56
    invokeLater
    -0.55
    rungsseite
    -0.54
    исленность
    -0.52
    RowIndex
    -0.50
     p
    -0.50
    TintMode
    -0.50
    iomanip
    -0.49
    بق
    -0.48
    POSITIVE LOGITS
    expandindo
    0.56
    FXMLLoader
    0.55
    IonicModule
    0.51
    WebVitals
    0.50
     for
    0.49
    occupe
    0.49
    explique
    0.47
     kautta
    0.45
    }}]{
    0.44
    friger
    0.44
    Activations Density 0.019%

    No Known Activations