© 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. 22-RES-MATRYOSHKA-DC
    7. 1931
    Prev
    Next
    INDEX
    Explanations

    the term 'System.' followed by a number

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -0.87
     himſelf
    -0.85
     Jefus
    -0.85
     שוליים
    -0.82
    sizeCache
    -0.81
    sidemargin
    -0.80
     Efq
    -0.78
     themſelves
    -0.77
     Chrift
    -0.76
     ſhe
    -0.76
    POSITIVE LOGITS
     systems
    1.19
     Systems
    1.07
     SYSTEMS
    0.99
    wide
    0.91
    systems
    0.90
    atics
    0.89
    Systems
    0.89
    atically
    0.88
     System
    0.88
     system
    0.87
    Activations Density 0.277%

    No Known Activations