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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11080
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and notations used in statistical modeling and proofs

    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
    EndProject
    -0.66
     المعيارى
    -0.66
     espirituales
    -0.56
    Trichloroethane
    -0.54
     femininas
    -0.52
    matchCondition
    -0.49
     disponibilités
    -0.49
    XmlAccessorType
    -0.49
     scienza
    -0.48
     gimnasio
    -0.47
    POSITIVE LOGITS
    AccessorTable
    0.68
    orios
    0.65
    dip
    0.61
    luß
    0.61
    __((
    0.60
    agoza
    0.59
     gu
    0.57
    پیوند
    0.57
     static
    0.57
     ostavi
    0.57
    Activations Density 0.584%

    No Known Activations