© 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. 18604
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and labels associated with data sets

    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
    <eos>
    -0.52
    ↵
    -0.51
    item
    -0.51
     for
    -0.50
     (
    -0.50
     E
    -0.50
    Items
    -0.49
     
    -0.49
     pas
    -0.48
     .
    -0.47
    POSITIVE LOGITS
     myſelf
    1.15
     BoxDecoration
    1.10
     itſelf
    1.02
     Efq
    1.01
     للاسماء
    0.99
    ſelves
    0.98
     photolibrary
    0.97
     Forumite
    0.97
    PreExecute
    0.96
     Majefty
    0.96
    Activations Density 0.005%

    No Known Activations