© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11976
    Prev
    Next
    INDEX
    Explanations

    occurrences of descriptions of legal or regulatory violations or infractions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     happens
    -1.45
     happen
    -1.35
    happens
    -1.34
    happen
    -1.21
     Happens
    -1.20
     HAPP
    -1.09
     happening
    -1.01
     Happen
    -0.95
     gebeurt
    -0.85
     händer
    -0.75
    POSITIVE LOGITS
     occurred
    1.57
     occured
    0.64
    ArgsConstructor
    0.63
    sizeCache
    0.57
    Personendaten
    0.56
    crumbs
    0.56
    contentLoaded
    0.54
    processable
    0.53
     ocorreu
    0.50
    водства
    0.50
    Activations Density 0.003%

    No Known Activations