© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3393
    Prev
    Next
    INDEX
    Explanations

    transitions/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
    AddTagHelper
    -0.84
    RectangleBorder
    -0.83
    URLException
    -0.82
    awtextra
    -0.72
    /**
    -0.66
     initComponents
    -0.65
    expandindo
    -0.65
     disambiguazione
    -0.63
    NUMX
    -0.63
    
    -0.63
    POSITIVE LOGITS
     most
    0.66
    tonsoft
    0.53
    seater
    0.48
     Most
    0.48
    ylus
    0.48
    Most
    0.46
     only
    0.46
     significant
    0.45
     respectively
    0.44
     quite
    0.41
    Activations Density 0.003%

    No Known Activations