© 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. 20200
    Prev
    Next
    INDEX
    Explanations

    patterns or structures related to numerical data or coding elements

    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
     myſelf
    -0.96
     Theſe
    -0.95
     purpoſe
    -0.94
     Diſ
    -0.94
     pleaſure
    -0.87
     Chriftian
    -0.86
     houſe
    -0.85
     reaſon
    -0.85
     Anſ
    -0.84
     Reſ
    -0.84
    POSITIVE LOGITS
    homonymie
    0.66
    sizeCache
    0.55
    MathML
    0.53
    ordu
    0.53
     A
    0.50
    hicles
    0.49
    ym
    0.48
     Mol
    0.47
    stalt
    0.46
    enterio
    0.46
    Activations Density 0.034%

    No Known Activations