© 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. 7082
    Prev
    Next
    INDEX
    Explanations

    discussions or content related to professional training and education

    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
     teach
    -1.21
     taught
    -1.06
     teaches
    -1.05
    teach
    -1.02
     Teach
    -1.01
     TEACH
    -1.01
    Teach
    -0.98
     exercise
    -0.93
     Taught
    -0.91
     instruct
    -0.90
    POSITIVE LOGITS
     training
    1.82
     Training
    1.78
    Training
    1.73
    training
    1.70
     TRAINING
    1.64
    TRAINING
    1.47
     trainings
    1.06
     Trainings
    1.03
     treinamento
    1.01
     trainees
    0.86
    Activations Density 0.008%

    No Known Activations