© 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. 22655
    Prev
    Next
    INDEX
    Explanations

    information related to marriages and family relationships

    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
     للمعارف
    -0.87
    kegaard
    -0.76
     NDEBUG
    -0.75
    Viitteet
    -0.74
     estekak
    -0.72
    اریخ
    -0.68
     виправивши
    -0.67
     itſelf
    -0.66
     vypl
    -0.65
     للاسماء
    -0.65
    POSITIVE LOGITS
    tagHelper
    0.53
     onItemClick
    0.46
    CDATA
    0.46
     produce
    0.45
    cracker
    0.45
    listFiles
    0.42
    خت
    0.41
     skal
    0.41
    ueras
    0.41
     producir
    0.40
    Activations Density 0.020%

    No Known Activations