© 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. 9162
    Prev
    Next
    INDEX
    Explanations

    terms related to medical prescriptions and pharmacology

    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
     الحره
    -0.55
    GraphicsUnit
    -0.50
     por
    -0.50
    KEYCODE
    -0.48
     mesa
    -0.48
    WriteLiteral
    -0.47
     der
    -0.47
    .*")]
    -0.46
    gaver
    -0.45
    QUIR
    -0.45
    POSITIVE LOGITS
     itſelf
    0.88
     doubtnut
    0.83
     ་་
    0.78
    ſelves
    0.75
     ―――――
    0.73
    ſelf
    0.70
    ."</
    0.70
     Anſ
    0.69
     pleaſure
    0.67
     faſt
    0.66
    Activations Density 0.010%

    No Known Activations