© 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. 16797
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks or conjunctions that indicate structure in 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
    preventDefault
    -0.55
    mstyle
    -0.48
    ská
    -0.46
     də
    -0.46
     weigh
    -0.46
     Zwick
    -0.45
     przewod
    -0.45
    ỏa
    -0.44
    گانه
    -0.44
    prepareStatement
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    1.05
    mybatisplus
    0.76
    abestanden
    0.76
     EconPapers
    0.74
     فريبيس
    0.71
    
    0.70
    Geplaatst
    0.69
    脚注の使い方
    0.69
    ibatis
    0.68
    ViewFeatures
    0.67
    Activations Density 0.000%

    No Known Activations