© 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. 2660
    Prev
    Next
    INDEX
    Explanations

    references to the name or concept of "Lam" or "Lamas"

    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
    ymce
    -0.68
     Solon
    -0.59
     chi̍t
    -0.57
     Lyn
    -0.56
     Carthag
    -0.54
    XmlAccessType
    -0.53
    leit
    -0.52
    Rival
    -0.52
    eux
    -0.52
     Machado
    -0.52
    POSITIVE LOGITS
     Lam
    3.09
    Lam
    3.03
     LAM
    2.61
    LAM
    2.45
     lam
    2.39
    lam
    2.22
     Lamb
    1.91
    Lamb
    1.83
     lamb
    1.79
    lamb
    1.62
    Activations Density 0.015%

    No Known Activations