Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 30970
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in code

    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
    gibt
    -0.40
    downarrow
    -0.38
     fik
    -0.37
    AlterField
    -0.37
    utsal
    -0.37
     hàng
    -0.36
    setPreferred
    -0.35
    setContent
    -0.35
    givers
    -0.34
    \_
    -0.34
    POSITIVE LOGITS
    TagMode
    1.02
    CloseOperation
    0.95
    utilisons
    0.78
    windowFixed
    0.75
    RenderAtEndOf
    0.72
     فريبيس
    0.72
    expandindo
    0.71
     للاسماء
    0.71
    posedge
    0.70
    rungsseite
    0.69
    Activations Density 0.048%

    No Known Activations