© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9139
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the URL format in text

    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
    Negative Logits
    featureID
    -0.51
    熟悉的
    -0.48
    nofollow
    -0.46
     transfieras
    -0.44
    Filmographie
    -0.43
    ItemBackground
    -0.42
     volte
    -0.41
    berdayakan
    -0.41
     ErrIntOverflow
    -0.41
    Rüyada
    -0.41
    POSITIVE LOGITS
    subplots
    0.74
     ioutil
    0.71
     Efq
    0.70
    GHIJKLM
    0.68
    براير
    0.66
     sumpay
    0.66
    buntu
    0.62
    stdafx
    0.61
    athyroid
    0.61
    GetAxis
    0.61
    Activations Density 0.000%

    No Known Activations