© 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. 6416
    Prev
    Next
    INDEX
    Explanations

    references to types of bubbles or bubblegum

    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
    offsetY
    -0.73
    IntoConstraints
    -0.71
    UpInside
    -0.66
    enoord
    -0.66
    DockStyle
    -0.66
    awtextra
    -0.66
     Goliath
    -0.65
     Montagu
    -0.65
     McRae
    -0.64
    
    -0.64
    POSITIVE LOGITS
     bubble
    3.64
     bubbles
    3.38
     Bubble
    3.27
    bubble
    3.17
    Bubble
    3.02
     Bubbles
    2.77
    bubbles
    2.69
     BUB
    2.45
    Bubbles
    2.27
     burbuja
    2.19
    Activations Density 0.002%

    No Known Activations