© 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. 2-RES-MATRYOSHKA-DC
    7. 3603
    Prev
    Next
    INDEX
    Explanations

    sequences containing the pattern "af" with high confidence

    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
    -------------</
    -0.69
    walla
    -0.66
     Huy
    -0.63
     Gra
    -0.56
     crack
    -0.56
     CRC
    -0.56
     Vign
    -0.55
    stin
    -0.54
    зулта
    -0.54
    arri
    -0.54
    POSITIVE LOGITS
    af
    3.25
    AF
    2.89
     AF
    2.77
     af
    2.73
     Af
    2.39
    Af
    2.36
    afs
    1.57
     AFB
    1.42
    afd
    1.38
    AFN
    1.35
    Activations Density 0.019%

    No Known Activations