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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19685
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the presence of "the" in varying contexts

    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
     and
    -0.49
    ══
    -0.48
     the
    -0.45
     lejos
    -0.42
    jár
    -0.40
     enough
    -0.40
    InsertCommand
    -0.40
    :
    -0.38
     their
    -0.38
     in
    -0.38
    POSITIVE LOGITS
    TypedDataSet
    0.99
     تضيفلها
    0.98
    KURZBESCHREIBUNG
    0.90
    WebElementEntity
    0.83
     مشين
    0.78
    ########.
    0.77
    Hentet
    0.77
     estimés
    0.77
    ContentAsync
    0.76
    AddTagHelper
    0.73
    Activations Density 0.128%

    No Known Activations