© 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. 0-RES-MATRYOSHKA-DC
    7. 13662
    Prev
    Next
    INDEX
    Explanations

    references to specific family members, particularly focusing on a son or children

    oai_token-act-pair · gpt-4.1-nano
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Their
    -0.58
     theirs
    -0.57
    Their
    -0.54
    WarningLevel
    -0.54
    heir
    -0.52
    epar
    -0.52
     note
    -0.49
    Coordenadas
    -0.49
     apprenticeship
    -0.47
     Biografie
    -0.47
    POSITIVE LOGITS
    hemiah
    0.74
    ChildScrollView
    0.62
    CppMethod
    0.61
     rospy
    0.61
     fallu
    0.61
    ⓧ
    0.61
     propOrder
    0.60
    RTEX
    0.59
     AppCompatTheme
    0.59
    granate
    0.58
    Activations Density 0.158%

    No Known Activations