© 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. 24947
    Prev
    Next
    INDEX
    Explanations

    terms related to cleanliness and the act of cleaning

    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
    Personensuche
    -0.98
    WebVitals
    -0.84
     AssemblyCulture
    -0.82
    twimg
    -0.82
    isks
    -0.82
    iettivo
    -0.80
     Numerade
    -0.79
     MainAxisSize
    -0.79
    seits
    -0.79
     Lordships
    -0.79
    POSITIVE LOGITS
     Clean
    0.81
     CLEAN
    0.81
     Eno
    0.76
    د
    0.74
    nola
    0.71
    ن
    0.71
    Clean
    0.69
     fin
    0.68
    CLEAN
    0.68
     sna
    0.67
    Activations Density 0.010%

    No Known Activations