© 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. 22-RES-MATRYOSHKA-DC
    7. 1619
    Prev
    Next
    INDEX
    Explanations

    words relating to patient care and business interactions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    PerformLayout
    -0.94
    IUrlHelper
    -0.91
    ValueStyle
    -0.87
    NameInMap
    -0.82
     تضيفلها
    -0.73
     mergeFrom
    -0.72
    Personendaten
    -0.72
    adpleegd
    -0.70
    bootstrapcdn
    -0.69
     ویکی‌پدی
    -0.67
    POSITIVE LOGITS
     satisfaction
    0.72
     friendly
    0.68
     rights
    0.60
     care
    0.59
     Satisfaction
    0.57
     centered
    0.56
    friendly
    0.55
     Cent
    0.54
     welfare
    0.53
     perception
    0.53
    Activations Density 0.955%

    No Known Activations