© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 557
    Prev
    Next
    INDEX
    Explanations

    code structures related to methods and function calls within programming

    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
    setContentView
    -0.54
     couverts
    -0.50
    dropIfExists
    -0.49
    новништво
    -0.47
     sonrisa
    -0.47
     transfé
    -0.46
     оригіналу
    -0.45
     Lives
    -0.45
     zit
    -0.45
     otomatig
    -0.45
    POSITIVE LOGITS
    IndentedString
    1.05
     Италијани
    0.79
     utafitiHapana
    0.74
    MessageOf
    0.73
    abestanden
    0.72
    oredCriteria
    0.71
    SharedCtor
    0.70
    évaluateur
    0.70
     myſelf
    0.69
     canlynol
    0.68
    Activations Density 2.062%

    No Known Activations