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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25711
    Prev
    Next
    INDEX
    Explanations

    the word "copy" in various contexts related to software licensing

    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
    
    -0.76
     surla
    -0.72
     nakalista
    -0.69
    Hozzáférés
    -0.68
    adaptiveStyles
    -0.66
    awakeFromNib
    -0.66
    aarrggbb
    -0.65
    RTLD
    -0.64
    uglify
    -0.63
    -0.63
    POSITIVE LOGITS
     copy
    0.63
     Copy
    0.51
    copy
    0.48
     henvisninger
    0.47
    Copy
    0.45
     Теперь
    0.44
    Ответ
    0.43
    eby
    0.43
     PRIZE
    0.43
     now
    0.42
    Activations Density 0.001%

    No Known Activations