© 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
    2. Gemma-2-2B
    3. 6-RES-MATRYOSHKA-DC
    4. 495
    Prev
    Next
    INDEX
    Explanations

    the word "or", optionally followed by determiners or other simple words

    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
    )");
    
    -0.81
    "])
    
    -0.80
    ++]
    -0.79
    "]);
    
    -0.77
    วก
    -0.69
    \"");
    -0.68
    subsection
    -0.66
    subsubsection
    -0.66
     ")");
    -0.66
    &
    
    -0.65
    POSITIVE LOGITS
     or
    1.82
     atau
    1.63
     eller
    1.63
     или
    1.55
     vagy
    1.44
    或
    1.43
     oder
    1.42
     یا
    1.41
     或
    1.41
     hoặc
    1.40
    Activations Density 1.299%

    No Known Activations