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. 18802
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and bracket punctuation

    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
    ghorn
    -0.52
     correctes
    -0.51
    MenuList
    -0.48
    ourites
    -0.48
    unningham
    -0.47
    ğından
    -0.47
    cerned
    -0.47
    ("~/
    -0.47
     idéia
    -0.47
    žek
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    1.10
    ChildScrollView
    0.85
    findpost
    0.82
     itſelf
    0.70
     '\\;'
    0.69
     mxArray
    0.68
    RectangleBorder
    0.68
    aarrggbb
    0.67
     تضيفلها
    0.67
    WriteTagHelper
    0.66
    Activations Density 0.101%

    No Known Activations