© 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. 17025
    Prev
    Next
    INDEX
    Explanations

    terms related to aerosol spray formulations

    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
    ScopeManager
    -0.75
     pyplot
    -0.71
     Goth
    -0.70
     iNdEx
    -0.68
     Warne
    -0.67
    Lazar
    -0.67
     htons
    -0.66
     Sonata
    -0.66
     Lazarus
    -0.65
    슷
    -0.65
    POSITIVE LOGITS
     Spray
    1.42
     spray
    1.41
    Spray
    1.41
    spray
    1.30
     sprays
    1.22
     aerosol
    1.20
     sprayed
    1.20
     spraying
    1.11
     Aerosol
    1.11
     aerosols
    1.02
    Activations Density 0.012%

    No Known Activations