© 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. 0-RES-MATRYOSHKA-DC
    7. 12102
    Prev
    Next
    INDEX
    Explanations

    references to blessings or curses

    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
    bless
    -0.80
     blessings
    -0.79
     blessing
    -0.77
     الحره
    -0.68
     leçon
    -0.66
     Segen
    -0.64
     تضيفلها
    -0.63
     béné
    -0.63
     الدولى
    -0.61
    SuppressMessage
    -0.59
    POSITIVE LOGITS
     Blessed
    3.23
    Blessed
    2.78
     blessed
    2.64
    blessed
    2.28
     blest
    1.29
     fortunate
    0.78
     privileged
    0.77
     cursed
    0.75
    cursed
    0.68
    fortunate
    0.63
    Activations Density 0.000%

    No Known Activations