© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 197
    Prev
    Next
    INDEX
    Explanations

    references to actions of making or creating

    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
    Personensuche
    -1.00
     titolata
    -1.00
    Награды
    -0.98
    ganggu
    -0.98
     AssemblyCompany
    -0.98
     comigo
    -0.94
     jPanel
    -0.94
     vectorielle
    -0.94
     contemporaine
    -0.93
     aphids
    -0.93
    POSITIVE LOGITS
     make
    1.83
     made
    1.77
    make
    1.75
    Make
    1.70
     Make
    1.70
     MAKE
    1.69
    made
    1.63
    MAKE
    1.63
     MADE
    1.57
    makes
    1.55
    Activations Density 0.909%

    No Known Activations