© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22284
    Prev
    Next
    INDEX
    Explanations

    terms related to bubbles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Frey
    -1.00
     Salisbury
    -0.91
    enoord
    -0.91
    }{*}{}
    -0.90
     Frey
    -0.88
     Normdatei
    -0.87
    writeString
    -0.86
    }{*}{
    -0.85
     MenuView
    -0.83
    BitmapFactory
    -0.82
    POSITIVE LOGITS
     bubble
    1.80
     bubbles
    1.74
     Bubble
    1.74
     Bubbles
    1.66
    Bubble
    1.58
    bubble
    1.55
    Bubbles
    1.50
    bubbles
    1.46
     BUB
    1.20
     burbuja
    0.91
    Activations Density 0.005%

    No Known Activations