© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16703
    Prev
    Next
    INDEX
    Explanations

    network configuration elements and socket details

    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
    MigrationBuilder
    -0.78
    itario
    -0.59
    OGND
    -0.58
     ویکی‌پدی
    -0.55
     Retriever
    -0.54
    BagLayout
    -0.53
    ExtendWith
    -0.52
    oplayer
    -0.51
    balleur
    -0.50
     protoimpl
    -0.50
    POSITIVE LOGITS
    ServerSocket
    0.62
    SocketAddress
    0.61
     relâche
    0.56
     partielle
    0.55
     olympiques
    0.52
     Superhost
    0.51
    PIA
    0.50
    createServer
    0.50
    igslist
    0.49
    tudes
    0.49
    Activations Density 0.050%

    No Known Activations