© 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. 22-RES-MATRYOSHKA-DC
    7. 59
    Prev
    Next
    INDEX
    Explanations

    various numeric and date formats, especially those used in scientific or mathematical contexts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    ⓧ
    -0.82
    хьтан
    -0.81
     שוליים
    -0.80
     مشين
    -0.78
    存于互联网档案馆
    -0.72
     Normdatei
    -0.71
    Билгалдахарш
    -0.71
     للمعارف
    -0.68
     Wikispecies
    -0.68
     ostavi
    -0.68
    POSITIVE LOGITS
     
    2.06
     eight
    0.77
     nine
    0.75
     seven
    0.70
    1
    0.66
     six
    0.66
     five
    0.65
     four
    0.65
     $
    0.65
     twenty
    0.61
    Activations Density 12.017%

    No Known Activations