© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5155
    Prev
    Next
    INDEX
    Explanations

    references to complex mathematical models and diagrams related to fitting, scaling, and analyzing data

    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
    Fig
    -0.84
     للمعارف
    -0.83
    httphttps
    -0.81
    EDEFAULT
    -0.63
    Composable
    -0.60
    LLocation
    -0.59
     IconData
    -0.57
     OnInit
    -0.57
    
    -0.57
    complexContent
    -0.56
    POSITIVE LOGITS
     Table
    1.83
    Table
    1.49
     Tables
    1.01
     table
    0.91
     TABLE
    0.89
    Таблица
    0.85
    Tables
    0.76
    Tabel
    0.72
     Tabla
    0.71
    Tabla
    0.66
    Activations Density 0.040%

    No Known Activations