© 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. 17511
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or statistical properties related to increasing values and rates in data analysis

    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
     newOwner
    -0.57
     ostavi
    -0.56
    aliers
    -0.52
    siębior
    -0.50
    ffler
    -0.50
    relativeTime
    -0.48
     stihl
    -0.48
    Décès
    -0.47
    lossians
    -0.47
    ieteur
    -0.47
    POSITIVE LOGITS
    RLock
    0.59
     fleste
    0.57
     obicei
    0.54
     entrare
    0.52
     flesta
    0.52
    RUnlock
    0.52
     dovuto
    0.50
    createForm
    0.50
     HttpNotFound
    0.50
     buone
    0.49
    Activations Density 0.035%

    No Known Activations