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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15538
    Prev
    Next
    INDEX
    Explanations

    references to legal evidence or procedural rulings

    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
     admission
    -1.05
     Admission
    -0.98
    Admission
    -0.82
     admissions
    -0.78
    admission
    -0.75
     Admissions
    -0.69
    /**
    -0.67
     confessions
    -0.61
     confession
    -0.60
    estin
    -0.54
    POSITIVE LOGITS
     admitted
    1.47
     المعيارى
    0.75
    iseries
    0.67
     فريبيس
    0.61
     comerciais
    0.61
    цездатний
    0.60
    XtraBars
    0.59
     digitais
    0.59
    StructEnd
    0.59
    łość
    0.59
    Activations Density 0.003%

    No Known Activations