© 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. 10922
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "start" and its variations 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
    ViewFeatures
    -0.87
     begun
    -0.86
     began
    -0.85
    began
    -0.82
    UserScript
    -0.78
    المناصب
    -0.77
    Tikang
    -0.75
    ;'>
    -0.75
    부터
    -0.74
     Began
    -0.74
    POSITIVE LOGITS
    ubility
    0.64
     waarde
    0.59
    t
    0.58
    maked
    0.57
     Sergi
    0.56
    T
    0.56
    rawDesc
    0.56
    Pall
    0.55
    ة
    0.55
     Villar
    0.54
    Activations Density 0.021%

    No Known Activations