© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14086
    Prev
    Next
    INDEX
    Explanations

    references to legal writs

    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
     JpaRepository
    -0.81
    setVerticalGroup
    -0.79
     iprot
    -0.76
    InstrumentedTest
    -0.76
     attitude
    -0.74
    StoryboardSegue
    -0.74
     cdti
    -0.73
    évaluateur
    -0.72
     مشين
    -0.71
     שוליים
    -0.70
    POSITIVE LOGITS
     writ
    2.61
     Writ
    1.38
    writ
    1.13
    Writ
    0.92
     wr
    0.70
    ulauan
    0.55
    XmlAccessType
    0.54
     WRIT
    0.52
    stru
    0.44
     au
    0.43
    Activations Density 0.002%

    No Known Activations