© 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. 5275
    Prev
    Next
    INDEX
    Explanations

    references to mathematical functions and their properties

    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
    ネート
    -0.48
    ymal
    -0.47
     vouloir
    -0.47
    ýš
    -0.46
    posals
    -0.46
    ichni
    -0.45
     disjoint
    -0.44
    ativement
    -0.44
    //
    -0.43
     всё
    -0.43
    POSITIVE LOGITS
    WebVitals
    0.77
     дописавши
    0.71
    invokeLater
    0.70
     تضيفلها
    0.68
    Manbalar
    0.66
     onCancelled
    0.66
    ArrowToggle
    0.65
    NamedQueries
    0.65
     AssemblyProduct
    0.64
    Sucesor
    0.64
    Activations Density 0.363%

    No Known Activations