© 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. 15506
    Prev
    Next
    INDEX
    Explanations

    references to a specific recurring entity or concept, likely an identifier or label used frequently throughout the text

    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
     Ann
    -1.06
     Мексичка
    -0.98
    WebVitals
    -0.92
     Anne
    -0.84
     Annals
    -0.83
     resourceCulture
    -0.81
     فريبيس
    -0.73
    ynchronously
    -0.73
    UnitTesting
    -0.71
    Personensuche
    -0.70
    POSITIVE LOGITS
    ann
    2.69
    ANN
    1.20
    annin
    0.93
    annan
    0.91
    annu
    0.84
    annas
    0.71
    annia
    0.70
    enn
    0.69
    annes
    0.54
     Horowitz
    0.54
    Activations Density 0.002%

    No Known Activations