© 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. 13561
    Prev
    Next
    INDEX
    Explanations

    email message headers

    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
     topics
    -0.72
    topics
    -0.66
     topic
    -0.63
    Topics
    -0.57
     Waray
    -0.57
     Topics
    -0.56
    topic
    -0.52
     temas
    -0.50
     theme
    -0.50
    TOPIC
    -0.49
    POSITIVE LOGITS
    Subject
    2.75
     Subject
    1.67
    SUBJECT
    1.40
    subject
    0.89
     SUBJECT
    0.88
    getSubject
    0.84
    setSubject
    0.83
     Comprometido
    0.79
     EconPapers
    0.79
    EndInit
    0.77
    Activations Density 0.002%

    No Known Activations