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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24278
    Prev
    Next
    INDEX
    Explanations

    phrases related to viral replication and immune response mechanisms

    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
     dati
    -0.47
     SafeArea
    -0.45
     Pohl
    -0.44
    IORITY
    -0.44
     aprendido
    -0.43
     pagado
    -0.43
     getService
    -0.42
     useContext
    -0.41
    Naomi
    -0.40
     overuse
    -0.40
    POSITIVE LOGITS
    WebElementEntity
    0.81
    CompilerServices
    0.79
    IInterface
    0.75
    TokenNameDOT
    0.70
     ویکی‌پدیا
    0.69
    RenderAtEndOf
    0.69
    thâu
    0.64
     MonoBehaviour
    0.61
    //
    0.61
    tanleria
    0.61
    Activations Density 0.052%

    No Known Activations