© 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. 18336
    Prev
    Next
    INDEX
    Explanations

    references to bottles in various contexts

    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
     AspNetCore
    -0.71
     xét
    -0.71
    XtraGrid
    -0.68
     McCarthy
    -0.65
    URLException
    -0.65
    &=&\
    -0.61
    mainPanel
    -0.60
     Sed
    -0.59
    [&
    -0.59
    misu
    -0.58
    POSITIVE LOGITS
     Bottle
    1.62
     bottle
    1.59
     Bottles
    1.56
    Bottle
    1.55
     bottles
    1.54
    bottle
    1.43
     BOTT
    1.38
    bottles
    1.33
     bottled
    1.27
     Bott
    1.25
    Activations Density 0.004%

    No Known Activations