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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11014
    Prev
    Next
    INDEX
    Explanations

    terms related to medical complications

    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
    ctrica
    -0.77
    BagConstraints
    -0.74
    MessageState
    -0.72
    ErrorResponse
    -0.70
    XmlAccessType
    -0.69
    BindView
    -0.68
    ContentAlignment
    -0.66
    CHELL
    -0.66
     Ag
    -0.63
     Holden
    -0.63
    POSITIVE LOGITS
     complications
    1.18
     complication
    1.09
     Complications
    1.05
    Complications
    0.93
     complicaciones
    0.91
     skut
    0.78
     efekty
    0.73
    PLICATIONS
    0.72
     complica
    0.70
    ToAction
    0.68
    Activations Density 0.007%

    No Known Activations