© 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. 3-RES-MATRYOSHKA-DC
    7. 639
    Prev
    Next
    INDEX
    Explanations

    the letter g in formulas or mathematical content

    oai_token-act-pair · gemini-2.0-flash
    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
    ArgumentParser
    -0.71
    jwa
    -0.62
     = 
    -0.59
    ArgsConstructor
    -0.57
    '){
    -0.57
    "){
    -0.57
     Guthrie
    -0.57
    Πε
    -0.56
    fortawesome
    -0.56
     Gira
    -0.55
    POSITIVE LOGITS
    g
    2.31
     g
    2.11
     G
    1.55
    G
    1.53
    ｇ
    1.05
    𝑔
    1.03
     г
    0.94
    𝘨
    0.94
    Gs
    0.93
    ɢ
    0.90
    Activations Density 0.765%

    No Known Activations