© 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. 2-RES-MATRYOSHKA-DC
    7. 3650
    Prev
    Next
    INDEX
    Explanations

    mentions of Pseudomonas aeruginosa and related bacterial pathogens

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.65
    jsdelivr
    -0.61
     LGB
    -0.58
     tap
    -0.54
    pa
    -0.53
     Roberts
    -0.52
    zeczy
    -0.52
    ("(
    -0.52
    breakable
    -0.52
     McDaniel
    -0.52
    POSITIVE LOGITS
     RA
    1.31
     BA
    1.22
     PA
    1.21
     MA
    1.19
     HA
    1.18
     TA
    1.14
     LA
    1.09
     DA
    1.08
     RI
    1.08
     GA
    1.05
    Activations Density 0.272%

    No Known Activations