Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 24409
    Prev
    Next
    INDEX
    Explanations

    terms related to the application or enforcing of legal provisions

    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
    SharedCtor
    -0.71
    RegistryLite
    -0.67
    WEBPACK
    -0.63
     chân
    -0.61
    asteroide
    -0.61
     eventdata
    -0.60
     BrowserModule
    -0.59
    "])
    
    -0.57
     <<<<<<<<<<<<<<
    -0.56
    blom
    -0.56
    POSITIVE LOGITS
    ExecuteReader
    0.76
    IBarButtonItem
    0.75
    bibitem
    0.67
     Tetrahedron
    0.67
    addMouseListener
    0.66
     Geophys
    0.62
    FFFFFF
    0.62
    WriteLiteral
    0.59
     majeure
    0.59
     Physica
    0.59
    Activations Density 0.019%

    No Known Activations