© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8503
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "the" 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
     rich
    -0.54
     pó
    -0.52
     N
    -0.50
    ած
    -0.50
    あれば
    -0.50
     And
    -0.49
    PHS
    -0.47
     scale
    -0.47
    нік
    -0.47
    guera
    -0.46
    POSITIVE LOGITS
    IsContent
    0.88
     surla
    0.85
    Vidite
    0.82
    Enllaces
    0.80
     pinulongan
    0.80
    kuuta
    0.77
    RectangleBorder
    0.76
    bkz
    0.74
    awtextra
    0.74
     allAfrica
    0.74
    Activations Density 0.052%

    No Known Activations