© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5039
    Prev
    Next
    INDEX
    Explanations

    the concept of extending or expanding

    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
     CreateTagHelper
    -0.82
     growth
    -0.78
     size
    -0.77
     GROWTH
    -0.76
    GOTREF
    -0.75
     Growth
    -0.75
    Growth
    -0.71
    size
    -0.69
    TabStop
    -0.67
     SIZE
    -0.66
    POSITIVE LOGITS
     extend
    2.81
     extended
    2.59
     extends
    2.56
     extending
    2.50
     Extend
    2.47
    extended
    2.42
     Extended
    2.38
    extend
    2.33
    Extended
    2.31
    Extend
    2.30
    Activations Density 0.048%

    No Known Activations