© 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. 21764
    Prev
    Next
    INDEX
    Explanations

    the word "that" in various contexts

    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
    ジェクト
    -0.66
    licants
    -0.57
     للاسماء
    -0.57
    віть
    -0.57
    URLException
    -0.56
    oyant
    -0.56
    ceptives
    -0.55
    .”)
    -0.54
    uitton
    -0.54
    zielle
    -0.54
    POSITIVE LOGITS
    Enllaces
    0.74
     hâte
    0.70
     venons
    0.68
     they
    0.65
     įsi
    0.63
     hivat
    0.62
     lèvres
    0.60
     setDate
    0.60
     cioè
    0.59
     quæ
    0.59
    Activations Density 0.027%

    No Known Activations