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. 20790
    Prev
    Next
    INDEX
    Explanations

    specific content type headers in a multipart data structure

    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
    ंड
    -0.51
    Membre
    -0.49
    '];?>
    -0.48
    vari
    -0.48
    Kernel
    -0.48
    "]}
    -0.47
     content
    -0.47
    uke
    -0.47
    Nederland
    -0.46
    zani
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.85
    ConstraintMaker
    0.81
    ImageContext
    0.79
    setViewportView
    0.76
    MemoryWarning
    0.74
     ProtoMessage
    0.73
     MainAxisSize
    0.73
    PreferredItem
    0.68
    SpringBootTest
    0.68
     agrí
    0.68
    Activations Density 0.002%

    No Known Activations