© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 281
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various contexts throughout the text

    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
    Viitteet
    -0.73
    #+#
    -0.68
    +:+
    -0.68
    rungsseite
    -0.66
    GeneratedValue
    -0.66
     &___
    -0.66
     ModelExpression
    -0.65
     كومونز
    -0.65
    Hentet
    -0.65
    DBNull
    -0.64
    POSITIVE LOGITS
     midst
    1.02
     وفي
    0.90
     vicinity
    0.81
    InThe
    0.79
     וב
    0.79
    inthe
    0.77
    Trong
    0.73
     Dalam
    0.71
    dalam
    0.70
     case
    0.66
    Activations Density 1.366%

    No Known Activations