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. 6438
    Prev
    Next
    INDEX
    Explanations

    instructions and queries related to programming and data handling in a technical context

    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
    </b>
    -0.75
    </strong>
    -0.67
    </h1>
    -0.65
    </h4>
    -0.54
     ddelweddau
    -0.54
    )}
    
    -0.54
    ContentAlignment
    -0.52
    </sub>
    -0.50
    )$}
    -0.50
    </h2>
    -0.49
    POSITIVE LOGITS
     Савезне
    0.78
     дописавши
    0.77
     initComponents
    0.77
     Lightboxes
    0.71
    MessageOf
    0.69
    IUrlHelper
    0.68
    BeginInit
    0.66
     relâche
    0.65
    InitStructure
    0.64
     تضيفلها
    0.64
    Activations Density 0.797%

    No Known Activations