© 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. 3150
    Prev
    Next
    INDEX
    Explanations

    the word "preliminary"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ambique
    -0.68
     sensibilité
    -0.66
     Schoen
    -0.63
     ویکی‌پدیا
    -0.63
    ceptre
    -0.63
    Affirmed
    -0.62
     LeBlanc
    -0.62
    GMENT
    -0.61
     Cline
    -0.61
     leksikon
    -0.61
    POSITIVE LOGITS
     preliminary
    2.89
     Preliminary
    2.73
    Preliminary
    2.64
    liminary
    2.55
     prelimin
    2.23
     preliminar
    2.11
     PRELIM
    2.03
    初步
    1.47
    liminaries
    1.25
     tentative
    1.21
    Activations Density 0.006%

    No Known Activations