© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 29554
    Prev
    Next
    INDEX
    Explanations

    terms related to winners and awards

    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
    robi
    -0.70
     lost
    -0.69
    icoot
    -0.65
     Fibers
    -0.59
    Losses
    -0.57
     lepas
    -0.57
     getAccount
    -0.56
     '*',
    -0.55
    Leif
    -0.55
     alimentaire
    -0.54
    POSITIVE LOGITS
     Winner
    0.91
     winners
    0.88
     winner
    0.84
     Winners
    0.82
     CWE
    0.75
    Winners
    0.72
    WINNER
    0.72
     WINNER
    0.72
    katapos
    0.72
    setContent
    0.71
    Activations Density 0.005%

    No Known Activations