© 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. 18-RES-MATRYOSHKA-DC
    7. 1637
    Prev
    Next
    INDEX
    Explanations

    technical language about pre-natal care, childhood and women's health

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     cherchés
    -0.53
     שוליים
    -0.48
     getActivity
    -0.46
    łbym
    -0.45
    ţional
    -0.44
    grà
    -0.44
    gradation
    -0.44
     Seel
    -0.43
     Zeno
    -0.43
     Utara
    -0.43
    POSITIVE LOGITS
     pregnant
    1.72
     pregnancy
    1.67
     Pregnancy
    1.51
     maternity
    1.48
     Pregnant
    1.45
    Pregnancy
    1.41
    pregnant
    1.38
     maternal
    1.37
     gestation
    1.37
     Maternity
    1.34
    Activations Density 1.146%

    No Known Activations