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. 30880
    Prev
    Next
    INDEX
    Explanations

    queries related to searching the internet

    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
    brainly
    -0.62
     الحره
    -0.55
    Chham
    -0.52
     producteur
    -0.50
    είται
    -0.49
     ویکی‌پدیا
    -0.47
    영어
    -0.47
    Exhibit
    -0.46
    ácara
    -0.46
    FormTagHelper
    -0.43
    POSITIVE LOGITS
    AndroidJUnit
    0.71
     تضيفلها
    0.62
     onCreateView
    0.58
     consultato
    0.58
     GetEnumerator
    0.56
    ClientSize
    0.56
     InputDecoration
    0.55
     références
    0.54
    oogle
    0.52
     LoggerFactory
    0.52
    Activations Density 0.010%

    No Known Activations