© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5402
    Prev
    Next
    INDEX
    Explanations

    terms related to set operations and mathematical expressions in programming or data processing contexts

    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
     Pries
    -0.63
     Emin
    -0.56
    xticks
    -0.54
    Caprio
    -0.53
    AppContext
    -0.52
     conosco
    -0.52
    cune
    -0.51
    Índice
    -0.51
     neutrality
    -0.50
    vereignty
    -0.50
    POSITIVE LOGITS
    strcat
    0.67
     merger
    0.66
     merge
    0.65
     merging
    0.65
    rrggbb
    0.65
    mergeFrom
    0.63
    融合
    0.63
    enumi
    0.61
    MergeFrom
    0.60
     fusion
    0.60
    Activations Density 0.408%

    No Known Activations