© 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. 13843
    Prev
    Next
    INDEX
    Explanations

    references to low-grade (less severe) metabolic acidosis cases

    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
    DockStyle
    -0.80
    :✨
    -0.67
     gyhoeddwyd
    -0.66
    исленность
    -0.62
     familie
    -0.52
    documentElement
    -0.52
     Raim
    -0.51
    Produzione
    -0.51
    SwingConstants
    -0.49
    ElementException
    -0.49
    POSITIVE LOGITS
    grade
    1.63
    grad
    1.02
    graded
    0.97
    grading
    0.84
    grades
    0.83
    GRADE
    0.77
    gradation
    0.69
    GRAD
    0.69
    grado
    0.69
     upgrades
    0.64
    Activations Density 0.001%

    No Known Activations