© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12925
    Prev
    Next
    INDEX
    Explanations

    references to negative public opinions or sentiments, particularly emphasizing negativity

    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
    ArrowToggle
    -0.65
     po
    -0.63
    po
    -0.55
    Lähteet
    -0.54
     worst
    -0.50
     Po
    -0.50
    ]=-
    -0.49
     "..\..\
    -0.49
    vtk
    -0.48
    Po
    -0.48
    POSITIVE LOGITS
     happy
    1.35
    happy
    1.19
     happiness
    1.12
     joyful
    1.12
     HAPPY
    1.12
     Happy
    1.11
     cheerful
    1.11
     heureux
    1.11
     happily
    1.10
     happier
    1.10
    Activations Density 0.007%

    No Known Activations