© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5679
    Prev
    Next
    INDEX
    Explanations

    statements indicating the outcome or conclusion

    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
    Preced
    -0.56
    Hop
    -0.48
     kal
    -0.48
     qualified
    -0.47
     choses
    -0.47
    尤
    -0.45
     препратки
    -0.45
     ac
    -0.45
     Qu
    -0.44
     often
    -0.44
    POSITIVE LOGITS
     result
    0.98
    result
    0.91
     результате
    0.86
     Folge
    0.86
    UnusedPrivate
    0.85
     Result
    0.81
    
    0.80
     conséquence
    0.79
    protoimpl
    0.78
    ագրություններ
    0.77
    Activations Density 0.022%

    No Known Activations