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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3478
    Prev
    Next
    INDEX
    Explanations

    terms indicating a high degree of severity in medical conditions or symptoms

    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
    躇
    -0.82
    illoma
    -0.81
    Ache
    -0.79
     disponibilités
    -0.77
     propOrder
    -0.76
     AUSSI
    -0.73
    RegistryLite
    -0.70
    multicolumn
    -0.67
     Mam
    -0.67
     Pickett
    -0.66
    POSITIVE LOGITS
     Severe
    1.06
    Severe
    0.95
    severe
    0.90
    Severity
    0.90
     Severity
    0.88
    Sever
    0.88
     severity
    0.84
     sério
    0.83
    SEVERE
    0.81
     severe
    0.80
    Activations Density 0.150%

    No Known Activations