© 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. 1-RES-MATRYOSHKA-DC
    7. 1530
    Prev
    Next
    INDEX
    Explanations

    references to statements emphasizing the significance or importance of a subject

    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
     Specific
    -0.95
     specific
    -0.91
    TypedDataSet
    -0.84
     للاسماء
    -0.80
    specific
    -0.79
    Specific
    -0.79
    opsida
    -0.75
     EconPapers
    -0.73
     exact
    -0.73
    DeleteBehavior
    -0.72
    POSITIVE LOGITS
     especially
    4.06
    Especially
    3.88
    especially
    3.81
     Especially
    3.80
     particularly
    3.48
    particularly
    3.31
     especialmente
    3.28
     Particularly
    3.28
     specialmente
    2.80
     особенно
    2.77
    Activations Density 0.068%

    No Known Activations