© 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. 6571
    Prev
    Next
    INDEX
    Explanations

    references to specific social or personal problems or issues

    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
    躇
    -0.80
    apunov
    -0.77
    strerror
    -0.71
    úgó
    -0.69
     photolibrary
    -0.68
     retrô
    -0.68
    uaikan
    -0.67
     setLoading
    -0.67
    RefNanny
    -0.66
    alnız
    -0.66
    POSITIVE LOGITS
    GEBURTSDATUM
    1.45
    MigrationBuilder
    0.99
    oredCriteria
    0.94
     resourceCulture
    0.93
     protoimpl
    0.91
     يتيمه
    0.91
    Identyfik
    0.90
    تقاوى
    0.89
     Roskov
    0.88
    EDEFAULT
    0.88
    Activations Density 4.293%

    No Known Activations