© 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. 11938
    Prev
    Next
    INDEX
    Explanations

    elements associated with message handling and data attributes in programming contexts

    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
     للمعارف
    -0.75
    occupe
    -0.47
    lenburg
    -0.46
     engagé
    -0.45
     cucchiaio
    -0.44
     def
    -0.44
     verrez
    -0.44
     كومونز
    -0.43
     indisponible
    -0.42
     кӀ
    -0.41
    POSITIVE LOGITS
    
    0.71
    __':
    0.71
    __":
    0.68
    __":
    0.67
     kaarangay
    0.67
     becauſe
    0.63
     }{@
    0.62
    PerformLayout
    0.61
     Monfieur
    0.61
    endwhile
    0.60
    Activations Density 0.016%

    No Known Activations