© 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. 3073
    Prev
    Next
    INDEX
    Explanations

    references to the chemical compound "CO" or "CO" represented as "carbon monoxide."

    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
    nalité
    -0.60
    standers
    -0.60
    haustible
    -0.59
     referenties
    -0.59
     considérons
    -0.57
    astéroïdes
    -0.57
    iredo
    -0.57
    junto
    -0.56
    meture
    -0.56
    OPSIS
    -0.56
    POSITIVE LOGITS
    co
    1.27
    ca
    1.16
    cas
    1.11
    c
    1.05
    cos
    1.00
    cor
    1.00
    cu
    0.98
    cus
    0.96
    com
    0.96
    car
    0.95
    Activations Density 0.462%

    No Known Activations