© 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. 13620
    Prev
    Next
    INDEX
    Explanations

    mentions related to feelings of loss or defeat

    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
     loose
    -1.52
     Loose
    -1.28
    Loose
    -1.27
    loose
    -1.26
     loosely
    -0.72
     looser
    -0.69
     loosened
    -0.63
     suel
    -0.61
    NOSTIC
    -0.60
     loos
    -0.57
    POSITIVE LOGITS
     losing
    2.06
     Losing
    1.70
    losing
    1.66
    Losing
    1.66
     loosing
    1.13
     perdiendo
    0.89
     winning
    0.89
    winning
    0.64
    tvguidetime
    0.61
    Winning
    0.59
    Activations Density 0.001%

    No Known Activations