© 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. 6-RES-MATRYOSHKA-DC
    7. 1463
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers related to quantity or order, such as "second", "third", "biggest", or "derivative," often alongside a qualifier like "most", "smallest."

    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
     first
    -0.84
    uerst
    -0.77
    unächst
    -0.72
     dulu
    -0.69
    FIRST
    -0.65
    начала
    -0.63
     первых
    -0.63
     FIRST
    -0.61
    pierw
    -0.60
     zuerst
    -0.59
    POSITIVE LOGITS
    Third
    1.29
     Third
    1.27
    third
    1.20
    Second
    1.17
     Second
    1.16
     Ninth
    1.16
     THIRD
    1.16
     third
    1.11
    second
    1.09
     fourth
    1.09
    Activations Density 0.448%

    No Known Activations