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. 16194
    Prev
    Next
    INDEX
    Explanations

    the definite article "the."

    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
     ExecuteAsync
    -0.71
     ویکی‌پدیای
    -0.69
    Билгалдахарш
    -0.68
    الحياه
    -0.63
     ProtoMessage
    -0.63
    :][
    -0.61
     nakalista
    -0.61
    gway
    -0.60
     Visser
    -0.59
    thenReturn
    -0.59
    POSITIVE LOGITS
    XmlAccessType
    0.54
    GroupLayout
    0.50
    Filmographie
    0.50
     againſt
    0.49
    TagHelper
    0.49
     Ikke
    0.48
    Non
    0.47
     houſe
    0.47
     Non
    0.46
     ſel
    0.46
    Activations Density 0.113%

    No Known Activations