© 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. 22-RES-MATRYOSHKA-DC
    7. 1764
    Prev
    Next
    INDEX
    Explanations

    words related to drilling or boring holes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    rungsseite
    -0.93
     ویکی‌پدیا
    -0.63
     Reverso
    -0.56
     Nimbus
    -0.54
    ContentAsync
    -0.53
    beu
    -0.53
     rolling
    -0.52
    umbent
    -0.50
    uxxxx
    -0.49
    Extinguishing
    -0.49
    POSITIVE LOGITS
     holes
    1.95
     hole
    1.88
     Hole
    1.77
    Hole
    1.73
     Holes
    1.71
     HOLE
    1.70
    holes
    1.66
    hole
    1.64
     openings
    1.60
    Holes
    1.56
    Activations Density 1.297%

    No Known Activations