© 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. 6321
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ok" or its variations

    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
     Kash
    -0.66
    onames
    -0.65
    Ẫ
    -0.62
    postmedia
    -0.61
    lename
    -0.60
     GetEnumerator
    -0.60
    )}-
    -0.59
     Nieren
    -0.57
     henvisninger
    -0.56
     permission
    -0.56
    POSITIVE LOGITS
    ok
    3.05
    OK
    2.92
     ok
    2.92
    Ok
    2.89
     OK
    2.81
     Ok
    2.72
     okay
    1.88
     alright
    1.73
    okay
    1.69
     OKAY
    1.55
    Activations Density 0.014%

    No Known Activations