© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10777
    Prev
    Next
    INDEX
    Explanations

    instances of crying or expressions of emotional distress

    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
     myſelf
    -0.80
     itſelf
    -0.78
     themſelves
    -0.75
     للاسماء
    -0.73
    #+#
    -0.73
     ―――――
    -0.69
     Cry
    -0.68
     Majefty
    -0.68
    InitVars
    -0.68
    Personendaten
    -0.68
    POSITIVE LOGITS
     cried
    2.30
     crying
    1.36
    Crying
    1.06
     wept
    1.05
     Crying
    1.04
     cries
    1.00
    crying
    0.93
     sobbed
    0.75
    哭
    0.66
     llorando
    0.65
    Activations Density 0.002%

    No Known Activations