© 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. 9034
    Prev
    Next
    INDEX
    Explanations

    references to trash and garbage disposal

    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
    Negative Logits
     Вікі
    -0.96
    ecap
    -0.83
     SafeMath
    -0.79
    RegressionTest
    -0.79
     ویکی‌پدیا
    -0.76
     AssemblyCulture
    -0.73
    +#+#
    -0.73
    jooq
    -0.72
    PreAuthorize
    -0.70
     suivez
    -0.70
    POSITIVE LOGITS
     trash
    1.34
     garbage
    1.15
    trash
    1.15
     Trash
    1.15
    garbage
    1.13
    Trash
    1.10
     Garbage
    1.08
    Garbage
    1.07
     junk
    1.00
     dumpster
    0.98
    Activations Density 0.010%

    No Known Activations