© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7584
    Prev
    Next
    INDEX
    Explanations

    references to large quantities, especially involving the concept of millions

    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
    Negative Logits
    ~\
    -0.63
     käs
    -0.59
     secteur
    -0.58
     CURIAM
    -0.56
    ivät
    -0.56
    huana
    -0.54
     ||
    -0.50
    PCS
    -0.49
     normalerweise
    -0.49
     cât
    -0.49
    POSITIVE LOGITS
     million
    2.52
     Million
    2.13
    million
    2.11
     MILLION
    1.98
    Million
    1.84
     millón
    1.66
     billion
    1.61
     miljoen
    1.60
     milhões
    1.50
     millones
    1.48
    Activations Density 0.022%

    No Known Activations