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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11409
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formulas involving variables and parameters in a specific context

    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
     giornal
    -0.46
    скоре
    -0.41
     sasaran
    -0.39
     itulah
    -0.39
    Étymologie
    -0.39
    henti
    -0.38
    zeiti
    -0.37
     potranno
    -0.37
     journée
    -0.37
     ilustraciones
    -0.37
    POSITIVE LOGITS
    ImageContext
    0.99
     propOrder
    0.98
    RenderAtEndOf
    0.97
     المعيارى
    0.91
    numerusform
    0.87
    sizeCache
    0.82
     EconPapers
    0.81
     препратки
    0.81
    expandindo
    0.81
    contentLoaded
    0.80
    Activations Density 0.026%

    No Known Activations