© 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. 13288
    Prev
    Next
    INDEX
    Explanations

    statements or content related to teaching or instructing

    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
     taught
    -0.73
     teaching
    -0.73
     Teaching
    -0.66
    Teaching
    -0.58
     TEACHING
    -0.57
    taught
    -0.54
    teaching
    -0.52
     Taught
    -0.50
    AndroidJUnit
    -0.47
     grà
    -0.47
    POSITIVE LOGITS
     Teach
    1.53
    Teach
    1.39
     teach
    1.23
    teach
    1.16
     teaches
    0.83
     TEACH
    0.81
    NUMX
    0.73
     endregion
    0.67
    — 
    0.66
    SharedCtor
    0.66
    Activations Density 0.002%

    No Known Activations