© 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. 19678
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical operations and 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
    évaluateur
    -0.85
    SequentialGroup
    -0.81
    TagMode
    -0.78
    SBATCH
    -0.77
     autorytatywna
    -0.76
    pexpr
    -0.73
    ValueStyle
    -0.72
     kasarigan
    -0.69
     مشين
    -0.69
    ISupport
    -0.68
    POSITIVE LOGITS
     JpaRepository
    0.48
    une
    0.45
     Wiktionnaire
    0.42
    ron
    0.41
     Dor
    0.38
    こちらも
    0.37
     anch
    0.37
    க்கும்
    0.36
    read
    0.36
    imize
    0.36
    Activations Density 0.204%

    No Known Activations