© 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. 22-RES-MATRYOSHKA-DC
    7. 3101
    Prev
    Next
    INDEX
    Explanations

    phrases about publishing and books

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ThroughAttribute
    -0.72
     CURIAM
    -0.58
    queryInterface
    -0.53
    InputTagHelper
    -0.52
    enterOuterAlt
    -0.51
    omány
    -0.49
    lorette
    -0.49
     betweenstory
    -0.48
    WriteBarrier
    -0.48
    zzlies
    -0.47
    POSITIVE LOGITS
     publishing
    1.73
     publication
    1.70
     publish
    1.66
     printing
    1.61
     published
    1.59
    publish
    1.52
     printed
    1.48
     Publish
    1.45
     print
    1.45
     publishes
    1.44
    Activations Density 0.313%

    No Known Activations