© 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. 12-RES-MATRYOSHKA-DC
    7. 15562
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to medical imaging and tumor analysis

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brut
    -0.49
     témoin
    -0.49
     pertes
    -0.44
     viso
    -0.44
     oignon
    -0.44
    titleMargin
    -0.43
     fasse
    -0.43
     drit
    -0.43
     ме
    -0.43
     confé
    -0.42
    POSITIVE LOGITS
    unhofer
    0.75
     doInBackground
    0.68
     gql
    0.65
    thâu
    0.65
     ApiException
    0.64
     للمعارف
    0.63
    SOUNDBITE
    0.62
    Predecesor
    0.61
    orianCalendar
    0.61
    writeFieldEnd
    0.61
    Activations Density 0.012%

    No Known Activations