© 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. 22854
    Prev
    Next
    INDEX
    Explanations

    phrases related to treatment interventions and outcomes in clinical settings

    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
     surla
    -0.72
     '{@
    -0.71
    HostException
    -0.69
     pinulongan
    -0.69
     AssemblyProduct
    -0.65
    ValueStyle
    -0.63
     editados
    -0.63
    <?
    -0.62
    انيف
    -0.60
    matchCondition
    -0.58
    POSITIVE LOGITS
    routeProvider
    0.47
     lengan
    0.43
     stay
    0.43
    tableFuture
    0.42
    erv
    0.42
    MLLoader
    0.42
    qas
    0.41
     trial
    0.41
     بيها
    0.41
    Stayed
    0.40
    Activations Density 0.068%

    No Known Activations