© 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. 2-RES-MATRYOSHKA-DC
    7. 6900
    Prev
    Next
    INDEX
    Explanations

    references to educational content or teaching

    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
    xticks
    -0.75
     training
    -0.70
    training
    -0.70
     Training
    -0.69
    Training
    -0.69
    TRAINING
    -0.67
     TRAINING
    -0.65
    runtime
    -0.59
    thik
    -0.57
     Lombardo
    -0.56
    POSITIVE LOGITS
     teach
    3.03
     teaching
    2.92
     Teaching
    2.80
     Teach
    2.75
    Teaching
    2.72
    teach
    2.72
     teaches
    2.66
    teaching
    2.63
    Teach
    2.61
     TEACHING
    2.53
    Activations Density 0.050%

    No Known Activations