© 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. 23283
    Prev
    Next
    INDEX
    Explanations

    terms related to intensive care and treatment units in a hospital setting

    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
    GEBURTSDATUM
    -0.83
    脚注の使い方
    -0.80
    idopsis
    -0.74
     Familienname
    -0.70
    varargin
    -0.68
    verständlich
    -0.67
    gebras
    -0.66
     Bello
    -0.66
    HostException
    -0.65
    ernalia
    -0.65
    POSITIVE LOGITS
     ICU
    0.81
    editMode
    0.57
    Lähteet
    0.54
    dtp
    0.50
    onekana
    0.50
    ICU
    0.48
    bigcap
    0.47
    生平
    0.47
     existence
    0.47
    study
    0.47
    Activations Density 0.004%

    No Known Activations