© 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. 10636
    Prev
    Next
    INDEX
    Explanations

    references to the term "Nitro" and its variations associated with chemical compounds

    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
    LLocation
    -0.69
     Charlene
    -0.68
    Cane
    -0.65
    orianCalendar
    -0.63
     Knapp
    -0.62
    ImageContext
    -0.62
     gener
    -0.60
    доми
    -0.60
     Lian
    -0.59
    enterOuterAlt
    -0.59
    POSITIVE LOGITS
     nitro
    1.11
     Nitro
    1.10
     nit
    1.09
    nitro
    1.03
    Nitro
    1.03
     Nit
    0.89
    Nit
    0.85
     NIT
    0.82
    nit
    0.78
     XCTest
    0.73
    Activations Density 0.006%

    No Known Activations