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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19228
    Prev
    Next
    INDEX
    Explanations

    URLs related to JavaScript libraries, particularly jQuery and Bootstrap

    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
     disambiguazione
    -1.04
    AddHtmlAttribute
    -0.82
     nakalista
    -0.73
    IntoConstraints
    -0.71
    Rüyada
    -0.69
     Chwiliwch
    -0.69
    EndProject
    -0.69
     ModelExpression
    -0.67
     autorytatywna
    -0.66
    Diwedd
    -0.66
    POSITIVE LOGITS
     tourmaline
    0.59
     poffible
    0.57
    okovic
    0.54
    Donkey
    0.53
     Barbuda
    0.52
     hobbit
    0.51
    dataflow
    0.50
     holog
    0.50
     Bikini
    0.49
     saucer
    0.49
    Activations Density 0.004%

    No Known Activations