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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19798
    Prev
    Next
    INDEX
    Explanations

    discussed elements pertaining to diversity and representation

    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
     Signalez
    -0.60
    twimg
    -0.55
     виправивши
    -0.55
    !("
    -0.52
    yfik
    -0.52
    Tembelea
    -0.52
    expandindo
    -0.50
    бенок
    -0.49
     AppModule
    -0.49
    Rhestr
    -0.49
    POSITIVE LOGITS
     houſe
    0.72
    contentLoaded
    0.71
     Somewhat
    0.69
     somewhat
    0.65
     iſt
    0.63
    somewhat
    0.61
     ſever
    0.60
    หน่อย
    0.60
    有些不
    0.59
     pleaſure
    0.59
    Activations Density 0.300%

    No Known Activations