© 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. 9301
    Prev
    Next
    INDEX
    Explanations

    specific dosages of medication

    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
    ")"
    -0.80
    ───
    -0.73
     useRouter
    -0.69
    슷
    -0.69
     Lauter
    -0.68
    ))*
    -0.67
     Trondheim
    -0.67
    "}"
    -0.66
    Cuáles
    -0.65
    yler
    -0.65
    POSITIVE LOGITS
     mg
    1.10
    mg
    0.93
     MG
    0.85
     Wiktionnaire
    0.83
     Mg
    0.82
    MG
    0.82
    SequentialGroup
    0.82
    elemField
    0.78
     GenerationType
    0.77
    afficheront
    0.74
    Activations Density 0.012%

    No Known Activations