© 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. 26179
    Prev
    Next
    INDEX
    Explanations

    references to complete entities or concepts within a context

    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
    enterOuterAlt
    -0.65
     HttpNotFound
    -0.64
     vPvB
    -0.63
    ArgsConstructor
    -0.62
    aarrggbb
    -0.61
     surla
    -0.59
    IGraphics
    -0.57
    IntoConstraints
    -0.57
    بوابة
    -0.56
     asiática
    -0.56
    POSITIVE LOGITS
     entire
    1.07
    entire
    0.99
     Entire
    0.91
     whole
    0.90
    Entire
    0.86
    whole
    0.84
     ENTIRE
    0.80
     inteiro
    0.77
     entirety
    0.70
    Whole
    0.69
    Activations Density 0.179%

    No Known Activations