© 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. 22784
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and closing braces

    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
    Personendaten
    -0.78
     الحره
    -0.70
    Personensuche
    -0.65
    <tr>
    -0.64
    ″]
    -0.63
    ❋
    -0.63
     ivelany
    -0.63
    </td>
    -0.62
    ']")
    -0.61
    chapper
    -0.60
    POSITIVE LOGITS
     vicenda
    0.65
     automatiques
    0.64
     plátano
    0.60
     rând
    0.60
     keç
    0.60
    ednesdays
    0.59
    Хро
    0.58
     keber
    0.58
    umption
    0.57
    nicity
    0.57
    Activations Density 0.039%

    No Known Activations