© 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. 1-RES-MATRYOSHKA-DC
    7. 671
    Prev
    Next
    INDEX
    Explanations

    references to the concept of greatness or something of exceptional quality

    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
     properly
    -0.68
     meglio
    -0.60
     profitably
    -0.59
     firmly
    -0.57
     correctement
    -0.56
     reasonably
    -0.56
     adequately
    -0.56
     صوتيه
    -0.56
    きちんと
    -0.54
     Properly
    -0.54
    POSITIVE LOGITS
     great
    4.06
    great
    3.95
    Great
    3.89
     Great
    3.81
    GREAT
    3.58
     GREAT
    3.48
     greate
    2.08
     greatness
    1.98
     greats
    1.98
    TheGreat
    1.84
    Activations Density 0.092%

    No Known Activations