© 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. 7374
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "stem" in various contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Demografía
    -0.53
     encu
    -0.52
    isance
    -0.52
    anInt
    -0.52
     المبار
    -0.52
     demografica
    -0.52
     Sand
    -0.50
     Monza
    -0.49
    férences
    -0.49
    appro
    -0.49
    POSITIVE LOGITS
     stem
    3.53
    stem
    3.16
     Stem
    3.16
    Stem
    3.03
     stems
    2.73
     stemmed
    2.17
    STEM
    1.91
     STEM
    1.73
     stemming
    1.62
    ステム
    1.47
    Activations Density 0.029%

    No Known Activations