© 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. 16805
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and to a lesser extent, variations of it in different 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
     the
    -0.82
     propOrder
    -0.71
    StoreMessageInfo
    -0.66
    Penulis
    -0.61
    Begriffsklä
    -0.60
    udic
    -0.59
    oa̍t
    -0.59
    RetentionPolicy
    -0.58
     아니라
    -0.58
    figer
    -0.57
    POSITIVE LOGITS
     Jefus
    0.69
     pleaſure
    0.67
     myſelf
    0.65
     muſt
    0.61
     Anſ
    0.60
     Heeren
    0.59
     ſever
    0.58
    ſelves
    0.57
     uſed
    0.57
     Efq
    0.57
    Activations Density 0.087%

    No Known Activations