© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32589
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duality or combinations

    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
    Negative Logits
     متعلقه
    -0.74
     חיצוניים
    -0.71
     Roskov
    -0.66
     صوتيه
    -0.61
     secondly
    -0.60
    IUrlHelper
    -0.60
     ExecuteAsync
    -0.59
     Secondly
    -0.57
    المناصب
    -0.57
     createSlice
    -0.57
    POSITIVE LOGITS
    GraphicsUnit
    0.56
    DBNull
    0.56
    Sucesor
    0.52
     تضيفلها
    0.51
    TextWatcher
    0.51
    adel
    0.48
     ويكيپيديا
    0.48
    riad
    0.47
     AssemblyCulture
    0.47
    nonatomic
    0.46
    Activations Density 0.015%

    No Known Activations