© 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. 12368
    Prev
    Next
    INDEX
    Explanations

    terms related to health policies and recommendations

    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
    Демографія
    -0.92
     @"/
    -0.84
    RegistryLite
    -0.84
     cherchés
    -0.83
     idéia
    -0.82
    rrggbb
    -0.79
    WebVitals
    -0.78
    MigrationBuilder
    -0.75
    TagMode
    -0.74
    CPtr
    -0.74
    POSITIVE LOGITS
     ‘
    0.52
     regular
    0.49
    ווה
    0.48
     (
    0.47
     offered
    0.46
    /
    0.44
     multiple
    0.44
     multi
    0.43
    <>();
    0.42
     associated
    0.42
    Activations Density 0.369%

    No Known Activations