© 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. 608
    Prev
    Next
    INDEX
    Explanations

    references to the authority "Ed" in legal or official documents

    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
    AndEndTag
    -0.81
    setVerticalGroup
    -0.67
     Bartol
    -0.64
     tartalomajánló
    -0.63
    بوابة
    -0.61
    PerformLayout
    -0.61
    saraba
    -0.58
     zvuky
    -0.57
     MonoBehaviour
    -0.57
     Joachim
    -0.57
    POSITIVE LOGITS
     Ed
    3.64
     ed
    3.63
    Ed
    3.58
    ed
    3.30
    ED
    2.94
     ED
    2.84
     eds
    2.16
    eds
    2.11
     Eds
    2.08
    Eds
    2.05
    Activations Density 0.205%

    No Known Activations