© 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. 14809
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals' names, especially "Miranda" and "Amar," indicating it detects mentions of particular people in the text

    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
    UnusedPrivate
    -0.71
    WebVitals
    -0.70
    balleur
    -0.69
     nakalista
    -0.66
    adaptiveStyles
    -0.66
    complexType
    -0.64
     beginnetje
    -0.63
    rawDesc
    -0.63
     Chbosky
    -0.63
    opheles
    -0.63
    POSITIVE LOGITS
     Amar
    0.94
    igs
    0.88
    Amar
    0.88
     amar
    0.86
     Miranda
    0.83
    imation
    0.75
    
    0.73
    amar
    0.70
    Miranda
    0.68
     Swanson
    0.68
    Activations Density 0.044%

    No Known Activations