© 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. 21937
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to congenital anomalies

    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
     дописавши
    -0.84
    évaluateur
    -0.84
    Попис
    -0.77
     SEDS
    -0.72
    WriteBarrier
    -0.71
    ViewImports
    -0.70
     Catawiki
    -0.69
     unknownFields
    -0.67
    orianCalendar
    -0.66
    astéroïdes
    -0.65
    POSITIVE LOGITS
     bawa
    0.49
    AddWithValue
    0.47
     lahir
    0.47
     Birth
    0.45
    HasKey
    0.45
     twin
    0.44
    cg
    0.43
    Birth
    0.42
    мыш
    0.42
    чої
    0.41
    Activations Density 0.029%

    No Known Activations