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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15333
    Prev
    Next
    INDEX
    Explanations

    instances of violations

    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
     violation
    -0.65
    violation
    -0.52
     infraction
    -0.51
     udrž
    -0.47
     Hurt
    -0.45
    றை
    -0.44
    uş
    -0.44
    SerializeField
    -0.44
    sic
    -0.44
     Violation
    -0.44
    POSITIVE LOGITS
     violates
    2.14
     violate
    2.03
     violating
    1.14
    )++;
    0.87
     contradicts
    0.82
    ^(@)
    0.80
     melang
    0.74
     >=",
    0.73
    WriteBarrier
    0.71
     Italijanski
    0.69
    Activations Density 0.001%

    No Known Activations