© 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. 693
    Prev
    Next
    INDEX
    Explanations

    discussions about the significance and interpretation of scientific facts versus meaningless facts

    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
     myſelf
    -0.74
    polation
    -0.74
    PERATURE
    -0.73
     Majefty
    -0.73
     ſta
    -0.72
     houſe
    -0.71
     pleaſure
    -0.71
     himſelf
    -0.70
    IFORNIA
    -0.70
     ſmall
    -0.70
    POSITIVE LOGITS
     onBind
    0.67
     jakby
    0.63
    HandlerContext
    0.60
     onOptions
    0.60
     AssemblyCulture
    0.58
     utafitiHapana
    0.58
     somehow
    0.56
     something
    0.54
    бенок
    0.54
     someone
    0.52
    Activations Density 1.153%

    No Known Activations