© 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. 12-RES-MATRYOSHKA-DC
    7. 3381
    Prev
    Next
    INDEX
    Explanations

    phrases related to adverse events and safety in clinical trials

    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
    Not in Any Lists

    No Comments

    Negative Logits
     hopeless
    -0.56
     saluto
    -0.49
     disambiguazione
    -0.47
    isław
    -0.46
     circumstance
    -0.45
     igno
    -0.45
     mass
    -0.42
     edin
    -0.42
     useless
    -0.42
     setStatus
    -0.42
    POSITIVE LOGITS
     Side
    0.72
    Side
    0.67
     Nebenwirkungen
    0.66
     side
    0.66
     Adverse
    0.65
    kloped
    0.64
     adverse
    0.63
    StoryboardSegue
    0.61
     Wicidata
    0.61
    Datuak
    0.59
    Activations Density 0.368%

    No Known Activations