© 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. 2-RES-MATRYOSHKA-DC
    7. 6116
    Prev
    Next
    INDEX
    Explanations

    references to crying or 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
     useRouter
    -0.75
    Portale
    -0.66
    postolic
    -0.65
     podjela
    -0.65
     McKee
    -0.63
    eloma
    -0.61
    TabIndex
    -0.57
    ýš
    -0.57
    cadilly
    -0.57
     Gantt
    -0.57
    POSITIVE LOGITS
     cry
    3.78
     Cry
    3.39
    Cry
    3.16
    cry
    3.03
     CRY
    2.88
     crying
    2.64
     cries
    2.63
     cried
    2.58
    CRY
    2.27
    crying
    2.27
    Activations Density 0.030%

    No Known Activations