© 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. 2-RES-MATRYOSHKA-DC
    7. 4887
    Prev
    Next
    INDEX
    Explanations

    references to specific parts of the human leg

    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
     архивлан
    -0.78
    kuuta
    -0.76
    Rhestr
    -0.72
    grà
    -0.72
    SafeArea
    -0.71
     tartalomajánló
    -0.69
    UpInside
    -0.69
     Rossetti
    -0.69
    Diwedd
    -0.67
     comuniques
    -0.66
    POSITIVE LOGITS
     leg
    3.50
     Leg
    2.92
    Leg
    2.81
    leg
    2.80
     legs
    2.53
     LEG
    2.45
     Legs
    2.19
    LEG
    2.11
    legs
    2.05
    legged
    1.93
    Activations Density 0.025%

    No Known Activations