© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4769
    Prev
    Next
    INDEX
    Explanations

    references to pain or pain-related sensations

    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
    PA
    -0.97
    pa
    -0.89
     PA
    -0.89
    MigrationBuilder
    -0.85
    Pa
    -0.85
     pa
    -0.84
     suffering
    -0.81
     Pa
    -0.80
     suffer
    -0.80
    hysema
    -0.79
    POSITIVE LOGITS
     Kul
    0.61
    DataAnnotations
    0.52
     fili
    0.52
     mouseClicked
    0.52
     لام
    0.52
    Portale
    0.51
     چراغ
    0.50
     commun
    0.50
    Vanjske
    0.49
     saf
    0.48
    Activations Density 0.005%

    No Known Activations