© 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. 12-RES-MATRYOSHKA-DC
    7. 928
    Prev
    Next
    INDEX
    Explanations

    numerical data related to medical statistics and clinical trial outcomes

    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
    GIVEREF
    -0.81
    elemField
    -0.69
    __":
    -0.65
    tagHelperRunner
    -0.65
     ModelRenderer
    -0.64
     onBind
    -0.64
    ="@+
    -0.63
     CreateTagHelper
    -0.63
     onCreateView
    -0.62
     MotionEvent
    -0.60
    POSITIVE LOGITS
     ComVisible
    0.47
    volmente
    0.45
     awal
    0.44
    ,
    0.44
     virtù
    0.41
    toHaveBeen
    0.41
     aksi
    0.41
    kannya
    0.40
    WithIOException
    0.40
     part
    0.39
    Activations Density 0.132%

    No Known Activations