© 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. 18-RES-MATRYOSHKA-DC
    7. 959
    Prev
    Next
    INDEX
    Explanations

    code snippets and URLs, especially those with parameters and redirects

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     Reverso
    -0.62
    yards
    -0.61
     cherchés
    -0.52
    usermodel
    -0.51
     يتيمه
    -0.51
     herum
    -0.50
    ingtones
    -0.49
     Kearns
    -0.48
     løpet
    -0.48
    ThroughAttribute
    -0.47
    POSITIVE LOGITS
     URL
    1.24
     url
    1.24
    url
    1.12
     Url
    1.11
    URL
    1.09
    Url
    1.06
     URLs
    1.02
    getUrl
    0.94
     URI
    0.93
     getUrl
    0.91
    Activations Density 1.258%

    No Known Activations