© 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. 11237
    Prev
    Next
    INDEX
    Explanations

    phrases related to data extraction and quality assessment in research studies

    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
     szól
    -0.55
    kloped
    -0.52
    segno
    -0.46
     exhibitions
    -0.44
    clip
    -0.43
    Gestures
    -0.43
     degener
    -0.42
    GRAPHIC
    -0.42
     لينك
    -0.42
    Crumb
    -0.42
    POSITIVE LOGITS
    createCell
    0.66
    AccessorTable
    0.66
    stateProvider
    0.64
     vVar
    0.62
    moveToFirst
    0.61
     wireType
    0.60
    GenerationType
    0.60
    MigrationBuilder
    0.60
    initWithFrame
    0.59
    colgroup
    0.59
    Activations Density 0.022%

    No Known Activations