© 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. 26015
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and their classifications, specifically leukemia and associated terms

    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
     flaps
    -0.47
    ban
    -0.46
    msgSender
    -0.44
    ál
    -0.42
    ولو
    -0.42
    }=\{
    -0.42
     Cortez
    -0.41
    ویی
    -0.41
     challeng
    -0.40
     decrees
    -0.40
    POSITIVE LOGITS
    fromnode
    0.83
    apimachinery
    0.70
     CURIAM
    0.69
     initComponents
    0.67
    Geplaatst
    0.67
    DotNetBar
    0.65
    :][
    0.64
    AlterField
    0.64
    المناصب
    0.63
    KommentareTeilen
    0.63
    Activations Density 0.113%

    No Known Activations