© 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. 0-RES-MATRYOSHKA-DC
    7. 10939
    Prev
    Next
    INDEX
    Explanations

    references to prosthetic devices or components

    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
     Савезне
    -0.92
    AsUp
    -0.84
     Италијани
    -0.75
    flink
    -0.70
    ]()
    -0.64
     Secund
    -0.64
    NUMX
    -0.63
    documentclass
    -0.63
    Zeneca
    -0.63
    RUnlock
    -0.63
    POSITIVE LOGITS
     prosthesis
    1.43
     prost
    1.08
     prosthetic
    1.08
     Prost
    1.00
    prost
    1.00
     neutro
    0.79
     mattress
    0.71
     prose
    0.66
     mattresses
    0.59
    legg
    0.54
    Activations Density 0.005%

    No Known Activations