© 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. 3-RES-MATRYOSHKA-DC
    7. 3391
    Prev
    Next
    INDEX
    Explanations

    the word "being"

    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
    Negative Logits
    findpost
    -0.68
    fecture
    -0.67
     Patt
    -0.61
     Faw
    -0.59
     kokona
    -0.59
     totalPrice
    -0.58
     McClure
    -0.57
     Patti
    -0.56
    awt
    -0.56
     nakalista
    -0.56
    POSITIVE LOGITS
     being
    1.81
     BEING
    1.59
     Being
    1.59
    Being
    1.57
    being
    1.55
     étant
    1.23
     fiind
    0.89
     bein
    0.87
     sendo
    0.84
     siendo
    0.82
    Activations Density 0.075%

    No Known Activations