© 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. 3-RES-MATRYOSHKA-DC
    7. 2143
    Prev
    Next
    INDEX
    Explanations

    sequences of capital letters, particularly "AA"

    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
     Iglesias
    -0.69
     ELL
    -0.64
     Hild
    -0.64
    Sass
    -0.64
    latz
    -0.64
     Lilly
    -0.62
     Chernobyl
    -0.62
     Rajesh
    -0.61
     Erle
    -0.61
    yadh
    -0.60
    POSITIVE LOGITS
    AA
    2.78
     AA
    2.53
    aa
    1.87
    AAA
    1.68
     aa
    1.54
     AAA
    1.46
    AAAA
    1.38
     Aa
    1.21
    Aa
    1.20
    aaa
    1.11
    Activations Density 0.018%

    No Known Activations