© 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. 30533
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare funding programs

    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
    copg
    -0.69
    Билгалдахарш
    -0.62
    ра
    -0.60
     Ane
    -0.56
    NOPQRST
    -0.56
     mView
    -0.56
     Hond
    -0.56
    WindowConstants
    -0.56
    editary
    -0.54
    balleur
    -0.53
    POSITIVE LOGITS
     Medicaid
    1.34
    Medica
    1.08
    ︎
    0.70
     Krä
    0.69
     androidx
    0.68
     palio
    0.67
    entially
    0.67
    oida
    0.66
     estekak
    0.66
     relais
    0.66
    Activations Density 0.001%

    No Known Activations