© 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. 31942
    Prev
    Next
    INDEX
    Explanations

    concepts related to comfort and tranquility versus the pressures of modern living

    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
     ratification
    -0.42
    Gain
    -0.41
    ทร
    -0.41
     aprovechar
    -0.41
    InvalidProtocol
    -0.41
     Convert
    -0.41
     revising
    -0.41
     hoarse
    -0.40
     gambe
    -0.40
     untapped
    -0.40
    POSITIVE LOGITS
    Hauptartikel
    0.78
    TagMode
    0.75
     ویکی‌پدیا
    0.72
     spoiled
    0.67
    ItemBackground
    0.67
    exitRule
    0.66
    WarningLevel
    0.66
    enderror
    0.65
    GEBURTSDATUM
    0.65
     HttpNotFound
    0.64
    Activations Density 0.163%

    No Known Activations