© 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. 3564
    Prev
    Next
    INDEX
    Explanations

    references to the hospital's safety and the hospital's ability to provide care

    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
    I
    -0.46
     I
    -0.43
    予
    -0.43
     L
    -0.40
    DebuggerNonUser
    -0.40
     Co
    -0.39
    ug
    -0.39
     būti
    -0.39
     To
    -0.39
    __*/
    -0.39
    POSITIVE LOGITS
    OGND
    0.87
    الحياه
    0.83
     Anſ
    0.81
    Portale
    0.75
     Bauhaus
    0.75
     Silurian
    0.74
    TagHelper
    0.73
    ształ
    0.73
    mberto
    0.73
    ValueStyle
    0.72
    Activations Density 0.600%

    No Known Activations