© 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. 24087
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and."

    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
     Efq
    -0.83
     كومونز
    -0.80
     itſelf
    -0.71
     poffe
    -0.70
     dévelo
    -0.69
     ControllerBase
    -0.67
     neceffary
    -0.67
     culturelles
    -0.67
     Majefty
    -0.66
     betweenstory
    -0.66
    POSITIVE LOGITS
     protoimpl
    0.55
     Wein
    0.47
    principalTable
    0.46
     ReactDOM
    0.46
     gặp
    0.43
    хьтан
    0.43
    WebElementEntity
    0.42
     Mary
    0.41
    суль
    0.41
     monoxide
    0.41
    Activations Density 0.000%

    No Known Activations