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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13981
    Prev
    Next
    INDEX
    Explanations

    references to the word "th" used as a numerical or ordinal marker

    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
     Th
    -1.10
    Th
    -0.91
     Thon
    -0.83
     thorium
    -0.73
    MLLoader
    -0.71
    awtextra
    -0.71
    
    -0.68
    ThroughAttribute
    -0.67
    useNewUrlParser
    -0.66
     Thri
    -0.65
    POSITIVE LOGITS
     th
    2.13
     tht
    0.65
     tha
    0.63
     t
    0.58
     loos
    0.53
     nd
    0.48
     "").
    0.48
     tb
    0.48
    ArrowToggle
    0.48
     tho
    0.48
    Activations Density 0.002%

    No Known Activations