© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1184
    Prev
    Next
    INDEX
    Explanations

    words related to science, medical treatments, and studies

    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
    Not in Any Lists

    No Comments

    Negative Logits
     results
    -0.61
    RESULTS
    -0.57
    Results
    -0.56
    results
    -0.54
     documented
    -0.52
     résultats
    -0.51
     RESULTS
    -0.51
    ⁡
    -0.51
     conducted
    -0.50
    confirmed
    -0.50
    POSITIVE LOGITS
     future
    0.90
     someday
    0.88
     künftig
    0.80
     therapeutics
    0.80
     zukünf
    0.79
     therapeutic
    0.79
    future
    0.77
    
    0.77
     prossimo
    0.77
     biotech
    0.77
    Activations Density 1.515%

    No Known Activations