© 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. 12077
    Prev
    Next
    INDEX
    Explanations

    expressions of negative or lamenting sentiment

    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
     recommandons
    -0.68
     moeite
    -0.58
     aproveitar
    -0.58
     unfortunate
    -0.50
     cavallo
    -0.49
     okaza
    -0.47
     IBOutlet
    -0.47
     pesar
    -0.47
     Aufwand
    -0.47
     overcast
    -0.46
    POSITIVE LOGITS
     sadly
    2.28
    Sadly
    1.95
     Sadly
    1.88
     tragically
    0.98
     thankfully
    0.96
     sorely
    0.86
     Thankfully
    0.85
     gravely
    0.84
    rungsseite
    0.75
    LookAnd
    0.75
    Activations Density 0.001%

    No Known Activations