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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13691
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific number or count, particularly the term "Three" appearing repeatedly

    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
    onAttach
    -0.59
    ãy
    -0.55
     Ten
    -0.54
    GetMapping
    -0.51
    UNRELATED
    -0.50
    SuppressLint
    -0.48
     Fourteen
    -0.48
    AccessException
    -0.47
    lulu
    -0.47
    PhysRevD
    -0.46
    POSITIVE LOGITS
     Three
    1.28
    Three
    1.16
    THREE
    0.88
    three
    0.73
     THREE
    0.73
    aarrggbb
    0.70
    ThroughAttribute
    0.69
     surla
    0.69
    ConstraintMaker
    0.68
     незавершена
    0.67
    Activations Density 0.004%

    No Known Activations