© 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. 26306
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting and mathematical symbols

    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
    Negative Logits
     Мексичка
    -1.26
    expandindo
    -1.19
    DrawerToggle
    -1.16
    +#+#
    -1.08
     tartalomajánló
    -1.06
     ویکی‌پدی
    -1.02
     &___
    -1.02
    ]='\
    -1.00
    #+#
    -1.00
    SBATCH
    -0.96
    POSITIVE LOGITS
    Oder
    0.52
    ↵↵
    0.48
    <h2>
    0.47
    <h3>
    0.47
    ↵
    0.46
    {
    0.46
    وظ
    0.45
    //
    0.44
     hemen
    0.44
    cin
    0.43
    Activations Density 0.048%

    No Known Activations