© 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. 9470
    Prev
    Next
    INDEX
    Explanations

    the presence of URLs

    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
    жу
    -0.41
     pi
    -0.36
    ِ
    -0.36
    <tbody>
    -0.35
    كا
    -0.35
    ensement
    -0.35
    [
    -0.35
    push
    -0.35
    になっています
    -0.34
    pi
    -0.34
    POSITIVE LOGITS
    الحياه
    1.16
     ویکی‌پدیا
    1.16
    GEBURTSDATUM
    1.06
    Personensuche
    1.01
    Geplaatst
    0.99
    ьаж
    0.98
    انيف
    0.93
    sidemargin
    0.90
    hoeddwyd
    0.89
     للاسماء
    0.89
    Activations Density 0.001%

    No Known Activations