© 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. 30140
    Prev
    Next
    INDEX
    Explanations

    bibliographic references and citations

    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
     Jefus
    -0.77
     ſeveral
    -0.75
     Efq
    -0.73
     myſelf
    -0.73
     fometimes
    -0.73
     Theſe
    -0.72
     becauſe
    -0.72
     Monfieur
    -0.71
     pleaſure
    -0.71
     whoſe
    -0.70
    POSITIVE LOGITS
    bib
    0.62
    باً
    0.57
     bib
    0.57
    Bib
    0.55
     المعيارى
    0.52
     Bib
    0.52
    клопе
    0.52
     CreateTagHelper
    0.52
    principalTable
    0.50
    semitism
    0.50
    Activations Density 0.003%

    No Known Activations