© 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. 10424
    Prev
    Next
    INDEX
    Explanations

    references to professional or expert titles

    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
    Negative Logits
     RIPRODUZIONE
    -0.71
     sẻ
    -0.71
    ioutil
    -0.67
    berdayakan
    -0.66
    RenderAtEndOf
    -0.65
     duquel
    -0.64
    antaranya
    -0.63
     gants
    -0.63
    astéroïdes
    -0.63
    érial
    -0.62
    POSITIVE LOGITS
     PROF
    1.60
    prof
    1.07
    Prof
    0.97
    PROF
    0.96
     profit
    0.89
     prof
    0.88
     Prof
    0.87
     Profit
    0.86
    profit
    0.83
    Profit
    0.80
    Activations Density 0.000%

    No Known Activations