© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 585
    Prev
    Next
    INDEX
    Explanations

    terminology, abbreviations, and references related to health questionnaires and clinical trials

    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
    .*")]
    -0.65
    posedge
    -0.62
    aarrggbb
    -0.62
    省市镇
    -0.60
    EDEFAULT
    -0.57
     actionMode
    -0.57
    hoeddwyd
    -0.55
     naturellement
    -0.55
    rrggbb
    -0.55
    tvguidetime
    -0.54
    POSITIVE LOGITS
     scale
    1.05
     scales
    0.94
     Scale
    0.94
     questionnaire
    0.90
     score
    0.85
     scoring
    0.85
    scale
    0.84
    Scale
    0.81
    scoring
    0.80
     Scales
    0.79
    Activations Density 0.965%

    No Known Activations