© 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. 6558
    Prev
    Next
    INDEX
    Explanations

    occurrences of the sequence "ou" in the text

    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
    WriteTagHelper
    -0.83
     dép
    -0.65
    UnsafeEnabled
    -0.57
    titial
    -0.55
    isel
    -0.54
     Pall
    -0.53
     Gale
    -0.52
     Fabian
    -0.51
    iak
    -0.51
    خاذ
    -0.51
    POSITIVE LOGITS
    ou
    3.44
    OU
    2.66
    Ou
    2.23
     Ou
    2.02
     ou
    1.81
     OU
    1.68
    ouc
    1.52
    hou
    1.42
    oug
    1.42
    tou
    1.38
    Activations Density 0.098%

    No Known Activations