© 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. 4-CLT-HP
    7. 4882
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
     MainAxisSize
    -0.63
     Theatres
    -0.59
     Denti
    -0.57
     PARENTS
    -0.55
     dad
    -0.55
    PARENT
    -0.54
     Parents
    -0.53
     Theaters
    -0.53
     Ples
    -0.52
    
    -0.52
    POSITIVE LOGITS
     AssemblyProduct
    0.70
     it
    0.69
    LookAnd
    0.57
    webElementXpaths
    0.55
    Externí
    0.54
     étoit
    0.52
    avimas
    0.51
    jsxFileName
    0.50
    الإنجليزية
    0.48
    ItemBackground
    0.47
    Activations Density 0.005%

    No Known Activations