© 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. 1-RES-MATRYOSHKA-DC
    7. 118
    Prev
    Next
    INDEX
    Explanations

    expressions of dissatisfaction, unhappiness, or passive-aggressive attitudes

    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
     Efq
    -1.43
     $_"
    -1.42
    ^(@)
    -1.41
     raiſ
    -1.36
     myſelf
    -1.36
     purpoſe
    -1.30
     photolibrary
    -1.30
     uſed
    -1.28
     Jefus
    -1.23
     greateſt
    -1.21
    POSITIVE LOGITS
    ↵↵
    1.18
     
    1.14
    ↵
    1.10
    .
    1.05
      
    0.96
    ,
    0.92
    <b>
    0.89
    ...
    0.88
     (
    0.87
    2
    0.85
    Activations Density 29.743%

    No Known Activations