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. 17137
    Prev
    Next
    INDEX
    Explanations

    terminology related to standards, ethics, and legal frameworks

    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
    клопе
    -0.66
     externi
    -0.60
    StreetMap
    -0.58
    Portály
    -0.56
    Bakgrunnsstoff
    -0.56
    bootstrapcdn
    -0.55
    <eos>
    -0.54
    ностран
    -0.54
    تقاوى
    -0.53
    Personensuche
    -0.53
    POSITIVE LOGITS
    Datuak
    0.60
    homonymie
    0.56
    
    0.52
    Rhestr
    0.51
    érables
    0.51
    bkz
    0.48
     LoginPage
    0.48
    Hozzáférés
    0.47
    página
    0.47
    ikiki
    0.47
    Activations Density 0.096%

    No Known Activations