© 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. 20930
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to data schema definitions

    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
    SequentialGroup
    -0.84
    RectangleBorder
    -0.82
     كومونز
    -0.77
    principalColumn
    -0.75
     ExecuteAsync
    -0.73
     незавершена
    -0.72
     дописавши
    -0.71
    Predecesor
    -0.71
    Sucesor
    -0.70
    Geplaatst
    -0.69
    POSITIVE LOGITS
    antía
    0.40
    <eos>
    0.40
    ="@+
    0.39
    rne
    0.38
    かん
    0.37
    addComponent
    0.37
     le
    0.36
    Xaml
    0.36
     Z
    0.36
     vecinos
    0.36
    Activations Density 0.145%

    No Known Activations