© 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. 2-RES-MATRYOSHKA-DC
    7. 4264
    Prev
    Next
    INDEX
    Explanations

    references to legal penalties related to offenses

    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
    MENAFN
    -0.98
     contextLoads
    -0.93
    ReusableCell
    -0.91
     ***!
    -0.87
    NUMX
    -0.84
    BeginContext
    -0.82
    setof
    -0.75
    Хьажоргаш
    -0.75
    ]';
    -0.74
    saraba
    -0.74
    POSITIVE LOGITS
     offense
    2.72
     offence
    2.41
     Offense
    2.17
     offenses
    2.02
     offences
    1.55
     offensive
    1.36
     offended
    1.14
     Offensive
    1.14
     offensively
    1.13
    offensive
    1.09
    Activations Density 0.027%

    No Known Activations