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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13892
    Prev
    Next
    INDEX
    Explanations

    references to interviews involving participants or witnesses

    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
    fjspx
    -0.77
     незавершена
    -0.71
     houſe
    -0.69
     Efq
    -0.68
     Theſe
    -0.65
     StringTokenizer
    -0.65
     whoſe
    -0.63
    ſelf
    -0.62
    FTFY
    -0.62
     Houſe
    -0.60
    POSITIVE LOGITS
     interviewed
    2.19
     questioned
    0.96
     interviewing
    0.96
     polled
    0.88
     surveyed
    0.79
     consulted
    0.78
     entrevist
    0.69
    
    0.63
     MainAxisSize
    0.58
     contacted
    0.57
    Activations Density 0.002%

    No Known Activations