© 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. 0-RES-MATRYOSHKA-DC
    7. 13016
    Prev
    Next
    INDEX
    Explanations

    mentions of the Slavic or Slavic-related groups, particularly "Sla" or "Slav", often as a reference to Slavs or Slavic peoples

    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
     paran
    -0.54
    Miri
    -0.54
    Connell
    -0.52
     apel
    -0.52
     Marqu
    -0.51
    ológico
    -0.51
    yafet
    -0.49
    ظ
    -0.48
     telef
    -0.47
    ByIndex
    -0.47
    POSITIVE LOGITS
     Sla
    3.16
     sla
    2.95
    Sla
    2.84
    sla
    2.77
     slam
    1.47
     slap
    1.43
     slams
    1.34
    slam
    1.33
     slaps
    1.31
     slapping
    1.30
    Activations Density 0.002%

    No Known Activations