© 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. 3457
    Prev
    Next
    INDEX
    Explanations

    the word "yeast" and words associated with organisms in a biology context

    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
     Parkes
    -0.59
     Indemnity
    -0.59
    kette
    -0.58
    wieś
    -0.58
     bangles
    -0.56
    copus
    -0.56
     Bondi
    -0.55
     Sieg
    -0.54
     cashmere
    -0.53
     cade
    -0.52
    POSITIVE LOGITS
     cerevisiae
    2.06
     yeast
    2.03
     fungi
    1.91
    Yeast
    1.88
     fungus
    1.87
     Yeast
    1.84
     fungal
    1.83
    visiae
    1.68
     Fungi
    1.54
    fung
    1.52
    Activations Density 0.179%

    No Known Activations