© 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. 164
    Prev
    Next
    INDEX
    Explanations

    code-related terms and syntax that pertain to variable declarations and dimensionality in programming and mathematical contexts

    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
    migrationBuilder
    -0.68
    jsxFileName
    -0.55
     floss
    -0.52
    Przypisy
    -0.48
     henvisninger
    -0.46
    gains
    -0.45
    jsdelivr
    -0.44
     fik
    -0.43
    CurrentValue
    -0.43
     WHO
    -0.43
    POSITIVE LOGITS
     sizeof
    0.69
     agrí
    0.68
     length
    0.68
     number
    0.67
     getItemCount
    0.66
    UnsafeEnabled
    0.66
    sizeof
    0.66
     تعداد
    0.64
     CreateTagHelper
    0.64
     numberOfRows
    0.64
    Activations Density 2.879%

    No Known Activations