© 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. 9411
    Prev
    Next
    INDEX
    Explanations

    medical tests and their related results

    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
    +#+
    -0.77
    ьаж
    -0.75
     }}"></
    -0.75
    Населення
    -0.73
    WriteTagHelper
    -0.71
    abetes
    -0.68
     exécu
    -0.68
     opérateur
    -0.66
    Obrázky
    -0.65
     "..\..\
    -0.64
    POSITIVE LOGITS
    HasAnnotation
    0.48
     predicting
    0.44
    য়
    0.42
    hezza
    0.42
    yfikacja
    0.42
    およ
    0.41
     incomplete
    0.40
    LAG
    0.40
    elin
    0.40
    EIN
    0.40
    Activations Density 0.371%

    No Known Activations