© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 11377
    Prev
    Next
    INDEX
    Explanations

    the term "Jr" indicating the generational suffix used in names

    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
    PerformLayout
    -0.75
     StringVar
    -0.66
    URLException
    -0.65
    intenance
    -0.62
    titleMargin
    -0.61
     prieten
    -0.61
     Planck
    -0.60
    MLLoader
    -0.58
    DBNull
    -0.58
    bombs
    -0.57
    POSITIVE LOGITS
     Jr
    0.80
    Sucesor
    0.66
    rungsseite
    0.59
     مواليد
    0.59
     jr
    0.58
    تقاوى
    0.57
    Jr
    0.56
    ISupport
    0.55
    Jereo
    0.53
     himself
    0.52
    Activations Density 0.007%

    No Known Activations