© 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. 11556
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical structures and notations

    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
    abetes
    -0.76
     Penh
    -0.76
    namentales
    -0.75
     NSCoder
    -0.69
    konos
    -0.66
    roblast
    -0.66
    makeText
    -0.65
     Cristian
    -0.65
    protoimpl
    -0.64
    rager
    -0.63
    POSITIVE LOGITS
    SpringBootTest
    0.69
    mathcal
    0.55
     Merz
    0.53
    AfterClass
    0.52
    füllung
    0.50
     Mier
    0.50
     Ching
    0.50
     يتيمه
    0.49
     hindurch
    0.49
     الرياضيه
    0.48
    Activations Density 0.066%

    No Known Activations