© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10832
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, often Neal, or mentions of damages, injuries, or damages-related terms

    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
    ankara
    -0.56
    disco
    -0.54
     Barracks
    -0.53
     Ign
    -0.51
    তথ্যসূত্র
    -0.51
    脚注の使い方
    -0.50
    graphicx
    -0.50
    Referências
    -0.49
     Henderson
    -0.48
     Flare
    -0.48
    POSITIVE LOGITS
    gants
    0.93
    Neal
    0.89
     Neal
    0.85
     disambiguazione
    0.80
    Transcription
    0.77
    thermia
    0.76
     bpy
    0.75
    ppler
    0.69
     beans
    0.68
     وتسجيلات
    0.67
    Activations Density 0.056%

    No Known Activations