© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 749
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to Javascript and APIs, also finding HTML tags

    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.22.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.22.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
    writeFieldEnd
    -0.79
    GEBURTSDATUM
    -0.71
    RenderAtEndOf
    -0.70
     виправивши
    -0.68
     snippetHide
    -0.67
     ['./
    -0.64
    expandindo
    -0.63
    ableness
    -0.62
     wireType
    -0.59
    期刊论文
    -0.59
    POSITIVE LOGITS
     id
    2.91
    id
    2.67
     ID
    2.58
     Id
    2.55
    Id
    2.52
    ID
    2.38
    getId
    1.94
     IDs
    1.92
    setId
    1.83
     ids
    1.82
    Activations Density 1.179%

    No Known Activations