© 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. 19143
    Prev
    Next
    INDEX
    Explanations

    numeric expressions and their patterns

    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
     leaſt
    -0.80
     leſs
    -0.73
    tably
    -0.69
     ویکی‌پدیای
    -0.69
     purpoſe
    -0.66
    strual
    -0.66
     houſe
    -0.65
    carteles
    -0.64
     sandero
    -0.64
    ={`${
    -0.63
    POSITIVE LOGITS
     الحره
    0.69
    ftagPool
    0.66
     CreateTagHelper
    0.60
    fillType
    0.59
     للمعارف
    0.57
     Infórmanos
    0.55
     المعرف
    0.55
    省市镇
    0.55
     consultato
    0.54
    CreateMap
    0.54
    Activations Density 0.120%

    No Known Activations