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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1012
    Prev
    Next
    INDEX
    Explanations

    Spreading or propagating

    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
    ếng
    -0.50
     in
    -0.47
     spread
    -0.46
    she
    -0.45
    enn
    -0.44
    spread
    -0.44
     Spread
    -0.43
     multiplic
    -0.43
    nexo
    -0.42
    homonymie
    -0.42
    POSITIVE LOGITS
     the
    0.87
     Infórmanos
    0.71
    JspWriter
    0.67
    LookAnd
    0.67
    HideFlags
    0.59
    MethodManager
    0.59
    WillAppear
    0.58
    DeleteBehavior
    0.57
    invokeLater
    0.57
    Према
    0.56
    Activations Density 0.002%

    No Known Activations