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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19122
    Prev
    Next
    INDEX
    Explanations

    references to influenza viruses

    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
     houſe
    -0.81
     Davey
    -0.79
     فريبيس
    -0.77
     Monfieur
    -0.74
     faſt
    -0.74
     innamor
    -0.73
     Raman
    -0.71
     stiefel
    -0.71
     Didier
    -0.69
     nameless
    -0.69
    POSITIVE LOGITS
     influenza
    1.05
     flu
    0.97
     Influenza
    0.97
     Flu
    0.86
    escaping
    0.68
    Flu
    0.68
    flu
    0.59
     FLU
    0.58
    FLU
    0.56
     Fla
    0.55
    Activations Density 0.002%

    No Known Activations