© 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. 6180
    Prev
    Next
    INDEX
    Explanations

    the presence of safety and health-related terms in medical contexts

    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
    oredCriteria
    -1.44
    Хьажоргаш
    -1.30
    Vidite
    -1.16
    省市镇
    -1.07
    RegistryLite
    -1.05
    TypedDataSet
    -1.01
    GEBURTSDATUM
    -1.01
    ніципа
    -0.98
    NameInMap
    -0.98
    sizeCache
    -0.95
    POSITIVE LOGITS
    WebControls
    0.53
    bootstrapcdn
    0.50
    styleUrls
    0.46
     onOptions
    0.45
     covered
    0.44
     ViewGroup
    0.41
    NSIndexPath
    0.41
     last
    0.41
    Referências
    0.41
    openConnection
    0.41
    Activations Density 3.994%

    No Known Activations