© 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. 6096
    Prev
    Next
    INDEX
    Explanations

    references to sorting functions or operations

    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
    Kalb
    -0.56
     Italijanski
    -0.55
     kind
    -0.50
    unnitel
    -0.46
    car
    -0.46
     Car
    -0.45
    UnusedPrivate
    -0.45
    CAR
    -0.45
    Kind
    -0.44
     Linien
    -0.44
    POSITIVE LOGITS
    Sort
    2.06
     Sort
    2.06
     Sorting
    2.02
     sorting
    1.98
     sorted
    1.95
    sort
    1.93
    SORT
    1.80
     SORT
    1.77
    Sorting
    1.74
    sorting
    1.73
    Activations Density 0.040%

    No Known Activations