© 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. 2707
    Prev
    Next
    INDEX
    Explanations

    references to awards and achievements in literature

    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
     Video
    -0.67
    Video
    -0.65
     video
    -0.63
     footage
    -0.63
    video
    -0.63
    VideoView
    -0.62
     videos
    -0.61
     VIDEO
    -0.58
    savevideo
    -0.57
     vídeo
    -0.56
    POSITIVE LOGITS
     writing
    0.93
     writers
    0.93
     readers
    0.89
     authors
    0.88
     author
    0.85
     writer
    0.84
    Writing
    0.84
    writing
    0.83
     Writing
    0.82
     novels
    0.80
    Activations Density 0.498%

    No Known Activations