© 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. 20535
    Prev
    Next
    INDEX
    Explanations

    terms related to economic policies and institutions, particularly those associated with the IMF and fiscal matters

    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
     ddelweddau
    -0.54
    WithIOException
    -0.53
    addComponent
    -0.52
    ChromeDriver
    -0.51
    DockStyle
    -0.48
    mmä
    -0.47
     COMMISSION
    -0.46
     вле
    -0.46
     terrest
    -0.45
     Kreuz
    -0.45
    POSITIVE LOGITS
    IMF
    0.78
     IMF
    0.72
     Exactos
    0.61
     austerity
    0.61
    DataAnnotations
    0.57
    AndPassword
    0.57
     nakalista
    0.57
     >=",
    0.57
    лтемелер
    0.56
     BeautifulSoup
    0.55
    Activations Density 0.046%

    No Known Activations