© 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. 0-RES-MATRYOSHKA-DC
    7. 15597
    Prev
    Next
    INDEX
    Explanations

    representations of the letter 'E' in various formats

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.53
    '])){
    -0.52
     %@",
    -0.50
    Scales
    -0.50
    '])){
    -0.49
    (")");
    -0.48
     оригіналу
    -0.47
     iprot
    -0.46
    TagMode
    -0.45
    eph
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.82
    
    0.77
     surla
    0.76
    NOPQRST
    0.73
    tvguidetime
    0.71
     EconPapers
    0.71
     AssemblyTitle
    0.70
    
    0.68
    ValueStyle
    0.66
    DockStyle
    0.65
    Activations Density 0.037%

    No Known Activations