© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128769
    Prev
    Next
    INDEX
    Explanations

    economic recession and bear market

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     persistently
    -0.07
    reached
    -0.06
     system
    -0.06
     limita
    -0.06
     insiders
    -0.06
    Trinity
    -0.06
     inexplic
    -0.05
    始终
    -0.05
     weer
    -0.05
     devido
    -0.05
    POSITIVE LOGITS
     szybko
    0.07
     Hadamard
    0.06
    ंटिक
    0.06
     verbinden
    0.06
     hızlı
    0.06
    Energie
    0.06
     across
    0.06
    pics
    0.06
     Nella
    0.06
    roskop
    0.06
    Activations Density 0.008%

    No Known Activations