© 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. 1-RES-MATRYOSHKA-DC
    7. 262
    Prev
    Next
    INDEX
    Explanations

    references to the number of items or instances, specifically mentioning "two" and "three."

    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
     every
    -0.88
     any
    -0.84
    EVERY
    -0.82
     EVERY
    -0.79
    ChildScrollView
    -0.77
    every
    -0.76
     many
    -0.75
     ANY
    -0.74
     all
    -0.73
     někter
    -0.71
    POSITIVE LOGITS
     two
    3.25
    two
    2.97
    Two
    2.78
     Two
    2.69
     deux
    2.55
     TWO
    2.53
    TWO
    2.48
     three
    2.41
     zwei
    2.34
    three
    2.23
    Activations Density 0.567%

    No Known Activations