© 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. 558
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and their associated figures or sections in a scientific document

    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
    futbolista
    -0.58
    }){
    -0.57
    "):
    -0.54
     karo
    -0.53
    ATURES
    -0.51
     Kran
    -0.49
    ցված
    -0.49
    었습니다
    -0.49
    ">(</
    -0.48
     `{
    -0.48
    POSITIVE LOGITS
     فريبيس
    0.77
    didSet
    0.76
     onOptions
    0.74
    出版年
    0.71
    fromnode
    0.68
    resave
    0.67
    pushFollow
    0.66
    GenerationType
    0.63
    ImageContext
    0.62
    DeleteBehavior
    0.60
    Activations Density 0.258%

    No Known Activations