© 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. 11397
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships and dependencies between elements

    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
     the
    -0.60
     that
    -0.57
     a
    -0.48
     seseorang
    -0.48
     väx
    -0.47
     itself
    -0.47
     igjen
    -0.47
     which
    -0.45
     precisely
    -0.44
     rând
    -0.44
    POSITIVE LOGITS
    脚注の使い方
    0.79
     intptr
    0.77
     AssemblyTitle
    0.77
    XmlAccessorType
    0.75
    Rohy
    0.74
    Portály
    0.73
     AssemblyCulture
    0.73
    IUrlHelper
    0.70
    GEBURTSDATUM
    0.70
    BindView
    0.69
    Activations Density 0.172%

    No Known Activations