© 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. 12-RES-MATRYOSHKA-DC
    7. 8815
    Prev
    Next
    INDEX
    Explanations

    directives related to compiler pragmas in code

    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
     asiatique
    -0.78
     étoit
    -0.71
     sauvage
    -0.71
     Shakspeare
    -0.71
     indisponible
    -0.70
     rempliss
    -0.70
     igenom
    -0.70
     stället
    -0.70
     inoxydable
    -0.69
     pouvoit
    -0.69
    POSITIVE LOGITS
    pragma
    2.88
    ragma
    1.63
    Pragma
    1.06
    "]').
    0.82
    Portail
    0.75
    ']").
    0.72
    ScopeManager
    0.69
    tagHelperRunner
    0.66
    Crom
    0.65
    tagHelper
    0.65
    Activations Density 0.001%

    No Known Activations