© 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. 11191
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities in the context of data or statistics

    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
    TagMode
    -0.79
     minimum
    -0.50
    Nhap
    -0.46
     sva
    -0.45
     exactement
    -0.45
    porre
    -0.44
     Minimum
    -0.44
    minimum
    -0.43
    тьяна
    -0.43
     satisfait
    -0.42
    POSITIVE LOGITS
    出版年
    0.84
    encodeWith
    0.83
     ostavi
    0.76
     cherchés
    0.74
    WriteBarrier
    0.66
     zelfs
    0.65
     estimés
    0.65
     nahilalakip
    0.63
    WriteLiteral
    0.62
    WEBPACK
    0.62
    Activations Density 0.122%

    No Known Activations