© 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. 12-RES-MATRYOSHKA-DC
    7. 11375
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ros" or variations of it in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     itſelf
    -1.09
     Monfieur
    -1.04
     Theſe
    -0.95
     Majefty
    -0.90
     himſelf
    -0.89
    SpringBootTest
    -0.89
     Jefus
    -0.87
     Efq
    -0.87
     ſmall
    -0.87
     becauſe
    -0.85
    POSITIVE LOGITS
     Ros
    1.74
    Ros
    1.66
     ROS
    1.30
     ros
    1.09
    ros
    1.06
     Rossi
    0.99
     Rosalind
    0.97
    ROS
    0.86
     Rosales
    0.82
     Zel
    0.74
    Activations Density 0.006%

    No Known Activations