© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17197
    Prev
    Next
    INDEX
    Explanations

    terms related to the administration of programs or services

    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
    Negative Logits
     Lue
    -0.70
    Fprintf
    -0.69
    ufficio
    -0.67
    ostic
    -0.65
     Joshi
    -0.65
     Figue
    -0.64
    USART
    -0.63
     jep
    -0.63
     Jozef
    -0.63
    део
    -0.62
    POSITIVE LOGITS
    ModelAdmin
    0.99
    administered
    0.92
     administered
    0.90
     administer
    0.84
    ISTRATION
    0.83
     administers
    0.81
     BorderRadius
    0.80
     administrations
    0.80
    adpleegd
    0.78
     administering
    0.78
    Activations Density 0.014%

    No Known Activations