© 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. 3-RES-MATRYOSHKA-DC
    7. 3321
    Prev
    Next
    INDEX
    Explanations

    the word "parent" followed by an underscore

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    addCriterion
    -0.79
    endphp
    -0.78
    Hentet
    -0.77
    aspectj
    -0.75
    TProtocol
    -0.68
     sons
    -0.67
    tonode
    -0.66
     AssemblyProduct
    -0.66
    FieldDescriptor
    -0.65
     resourceCulture
    -0.65
    POSITIVE LOGITS
    parent
    2.53
     parent
    2.52
     Parent
    2.34
    Parent
    2.30
     PARENT
    2.09
    PARENT
    2.06
     Parents
    1.55
     parental
    1.54
     getParent
    1.49
     parents
    1.48
    Activations Density 0.040%

    No Known Activations