© 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. 0-RES-MATRYOSHKA-DC
    7. 15721
    Prev
    Next
    INDEX
    Explanations

    references to specific legal codes or statutes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    TintMode
    -0.65
    dafx
    -0.65
    szönöm
    -0.65
    StoryboardSegue
    -0.61
     AssemblyVersion
    -0.58
    exao
    -0.56
    NameInMap
    -0.56
    Rujuakan
    -0.55
    spesies
    -0.55
    outState
    -0.55
    POSITIVE LOGITS
    ied
    3.55
    IED
    1.86
    ieds
    1.35
    iedo
    0.95
    iedz
    0.93
    ieden
    0.91
    iedy
    0.82
    ieder
    0.76
    ication
    0.75
    ying
    0.71
    Activations Density 0.001%

    No Known Activations