© 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. 721
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance or insignificance of a matter

    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
     *__
    -0.56
    onedDateTime
    -0.52
    ansı
    -0.49
    oubtedly
    -0.49
    hone
    -0.48
     Experiences
    -0.47
     experiences
    -0.46
    不得不
    -0.46
    dasarkan
    -0.45
    NotFoundError
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.85
     whatsoever
    0.76
     unimportant
    0.74
     متعلقه
    0.72
    ьаж
    0.71
    reportWebVitals
    0.71
    MigrationBuilder
    0.70
     harmless
    0.70
     matter
    0.69
    tagHelperRunner
    0.68
    Activations Density 1.056%

    No Known Activations