© 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. 3926
    Prev
    Next
    INDEX
    Explanations

    references to specific medical procedures, especially related to eye and hip surgeries

    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
    <eos>
    -0.73
    SequentialGroup
    -0.48
     $
    -0.43
     mascotas
    -0.41
     jasa
    -0.41
     volna
    -0.40
     Such
    -0.40
    also
    -0.40
    DebuggerNonUser
    -0.39
    BASEPATH
    -0.39
    POSITIVE LOGITS
     itſelf
    0.86
     purpoſe
    0.82
     fubject
    0.82
    esterday
    0.81
     ſche
    0.79
     myſelf
    0.79
     themſelves
    0.77
    脚注の使い方
    0.77
     reaſon
    0.75
     neceffary
    0.75
    Activations Density 1.803%

    No Known Activations