© 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. 0-RES-MATRYOSHKA-DC
    7. 15692
    Prev
    Next
    INDEX
    Explanations

    references to the activity of the angiotensin-converting enzyme, specifically "ocor" (likely referring to "ocor" in nucleotide sequences), indicating it detects mentions of angiotensin-related enzymatic activity

    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
    abestanden
    -0.64
    VideoCapture
    -0.53
    invert
    -0.52
    abos
    -0.50
    েই
    -0.50
     minOccurs
    -0.49
     velkommen
    -0.49
    ்த
    -0.49
     magnétique
    -0.47
    Sommer
    -0.47
    POSITIVE LOGITS
    ocor
    4.41
    ExtendWith
    0.79
    cortico
    0.67
    biamo
    0.66
    Personendaten
    0.63
    åringen
    0.61
    Referències
    0.59
    "}")
    0.59
     kasarigan
    0.58
     '\\;'
    0.57
    Activations Density 0.005%

    No Known Activations