© 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. 23976
    Prev
    Next
    INDEX
    Explanations

    phrases inviting reflection or consideration about a topic

    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
    -1.15
     وتسجيلات
    -1.04
    SourceChecksum
    -0.94
     مشين
    -0.89
    CppMethod
    -0.88
     jspb
    -0.87
    GIVEREF
    -0.82
    Vidite
    -0.80
    MENAFN
    -0.80
     تضيفلها
    -0.79
    POSITIVE LOGITS
    Imagine
    0.52
    你看
    0.49
     Say
    0.49
    perfor
    0.49
     Imagine
    0.47
     example
    0.47
     say
    0.46
    arbeit
    0.44
    Say
    0.44
     the
    0.43
    Activations Density 0.040%

    No Known Activations