© 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. 19636
    Prev
    Next
    INDEX
    Explanations

    numerical values and units related to mass and density in scientific 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
    verwijspagina
    -0.94
     تضيفلها
    -0.87
    fillType
    -0.75
    ValueStyle
    -0.73
    ImageContext
    -0.73
    ✨:
    -0.71
     normais
    -0.70
    inghouse
    -0.69
     Chwiliwch
    -0.69
    MessageTagHelper
    -0.68
    POSITIVE LOGITS
     pesa
    0.54
     gravit
    0.52
     invested
    0.51
     weigh
    0.50
    onAttach
    0.49
     sworn
    0.48
     weighed
    0.47
    gya
    0.47
     Aff
    0.46
     souff
    0.46
    Activations Density 0.012%

    No Known Activations