© 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. 25460
    Prev
    Next
    INDEX
    Explanations

    phrases indicating research findings or study outcomes

    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
     protoimpl
    -1.00
    styleType
    -0.97
    StoryboardSegue
    -0.87
    CloseOperation
    -0.86
    DebuggerNonUser
    -0.81
    AddHtmlAttribute
    -0.81
     كومونز
    -0.80
    sizeCache
    -0.76
     للاسماء
    -0.75
     Мексичка
    -0.74
    POSITIVE LOGITS
     ourselves
    0.92
     Our
    0.57
    Our
    0.55
    лим
    0.55
     Myself
    0.52
     our
    0.50
     vores
    0.48
    dze
    0.48
     نحن
    0.47
     myself
    0.46
    Activations Density 0.121%

    No Known Activations