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. 29672
    Prev
    Next
    INDEX
    Explanations

    parentheses and their usage within the text

    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
    BeginInit
    -0.93
    __':
    
    -0.79
    `;
    
    -0.69
    AndEndTag
    -0.68
     oprot
    -0.64
    "]);
    
    -0.62
     initComponents
    -0.61
     للاسماء
    -0.60
    ']);
    
    -0.60
    '];
    
    -0.59
    POSITIVE LOGITS
     series
    0.55
    msgTypes
    0.54
    Hentet
    0.53
    Initializable
    0.52
    曖昧さ回避
    0.50
    éndole
    0.49
    Object
    0.48
     now
    0.47
    strncmp
    0.46
    ータル
    0.46
    Activations Density 0.004%

    No Known Activations