© 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. 6119
    Prev
    Next
    INDEX
    Explanations

    terms related to medical therapies and treatments for diseases

    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
     itſelf
    -0.52
    abstractmethod
    -0.49
     usually
    -0.48
     station
    -0.47
     DialogResult
    -0.46
    Usually
    -0.46
    FirebaseDatabase
    -0.45
    ⁡
    -0.44
     lượt
    -0.44
     Usually
    -0.43
    POSITIVE LOGITS
    出版年
    0.67
    НИК
    0.64
    prnewswire
    0.63
    lgari
    0.62
    tinyos
    0.60
    ropia
    0.60
    tagHelperRunner
    0.59
    yntaxException
    0.59
    KEYCODE
    0.59
    ISupport
    0.58
    Activations Density 0.281%

    No Known Activations