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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 363
    Prev
    Next
    INDEX
    Explanations

    connections between health-related concepts and social or economic factors

    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
    ValueGenerated
    -0.75
     and
    -0.71
    BagLayout
    -0.67
    ContentAsync
    -0.66
    Hentet
    -0.65
    MemoryWarning
    -0.63
    Personendaten
    -0.62
     naselje
    -0.60
     OnInit
    -0.59
     мәкал
    -0.57
    POSITIVE LOGITS
    それに
    0.77
     importantly
    0.75
     consequent
    0.74
     consequently
    0.74
    何より
    0.74
     therefor
    0.71
     daarbij
    0.66
     subsequent
    0.65
     subsequently
    0.64
     consiguiente
    0.64
    Activations Density 4.450%

    No Known Activations