© 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. 25668
    Prev
    Next
    INDEX
    Explanations

    references to the nginx web server and associated configurations

    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
     zirc
    -0.60
     незавершена
    -0.60
     متعلقه
    -0.58
    uinal
    -0.57
    heureux
    -0.56
     understatement
    -0.56
    esgue
    -0.55
     boreal
    -0.52
    usammen
    -0.51
     BitmapFactory
    -0.50
    POSITIVE LOGITS
    GEBURTSDATUM
    0.61
     doInBackground
    0.58
    !*\
    0.57
    AddHtmlAttribute
    0.56
    GenerationType
    0.54
    şiv
    0.53
     Obrador
    0.52
     obje
    0.52
    FunctionFlags
    0.51
    aarrggbb
    0.49
    Activations Density 0.058%

    No Known Activations