© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16145
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to health and physical activity

    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
     صوتيه
    -1.01
    ConstraintMaker
    -0.69
     المعيارى
    -0.63
    Примітки
    -0.63
    perror
    -0.61
    ViewImports
    -0.60
     استنادى
    -0.59
     povezave
    -0.56
     intptr
    -0.56
    Egypte
    -0.56
    POSITIVE LOGITS
    queryInterface
    0.51
    Portail
    0.49
    Spare
    0.47
     Cess
    0.46
    oredCriteria
    0.45
    ceps
    0.45
    BuilderFactory
    0.45
    رشف
    0.45
     IFF
    0.45
     subtra
    0.44
    Activations Density 0.016%

    No Known Activations