© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 788
    Prev
    Next
    INDEX
    Explanations

    the word "th" as an ordinal suffix in dates or terms

    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
     Cæsar
    -1.04
    ExecuteReader
    -0.85
    er
    -0.80
    Mira
    -0.79
     Edy
    -0.79
    ]][
    -0.79
     Pico
    -0.79
     Miracles
    -0.79
    Resol
    -0.77
     Sarko
    -0.77
    POSITIVE LOGITS
     TH
    1.43
    th
    1.38
     Th
    1.38
    TH
    1.34
    Th
    1.26
     th
    1.19
     Thi
    1.17
    ATH
    1.11
     Tha
    1.09
     thi
    1.07
    Activations Density 1.145%

    No Known Activations