© 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. 3998
    Prev
    Next
    INDEX
    Explanations

    actions related to applying, adjusting, or modifying processes or tools

    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
     offers
    -0.68
     offering
    -0.63
     "
    -0.60
     improvement
    -0.56
     gains
    -0.55
     lies
    -0.54
     is
    -0.52
     shows
    -0.52
     answers
    -0.52
     deals
    -0.52
    POSITIVE LOGITS
     calibrate
    1.07
     stabilize
    1.03
     modulate
    1.02
    AsUp
    1.00
     mutate
    1.00
     decorate
    1.00
     localize
    0.98
     propagate
    0.98
     categorize
    0.97
     classify
    0.96
    Activations Density 1.139%

    No Known Activations