© 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. 11850
    Prev
    Next
    INDEX
    Explanations

    expressions related to grief and mourning

    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
    ">*
    -0.63
     sad
    -0.58
    Portale
    -0.56
     tingling
    -0.55
    cydow
    -0.55
    kwür
    -0.52
     virke
    -0.51
     நட
    -0.50
    endal
    -0.47
     Bismarck
    -0.47
    POSITIVE LOGITS
     grief
    3.36
     Grief
    2.55
    Grief
    2.17
     grieving
    2.02
     grieve
    1.97
     mourning
    1.81
     grieved
    1.54
     mourn
    1.45
     bereavement
    1.44
     bereaved
    1.38
    Activations Density 0.002%

    No Known Activations