© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130792
    Prev
    Next
    INDEX
    Explanations

    previously similar

    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
     diğer
    -0.07
     innych
    -0.06
     McIntyre
    -0.06
     Expected
    -0.06
     esperaba
    -0.06
     трансформа
    -0.06
     otros
    -0.06
    其他
    -0.06
     longed
    -0.06
    之下
    -0.06
    POSITIVE LOGITS
     previously
    0.08
    Similar
    0.08
    Previously
    0.07
     similar
    0.07
    previously
    0.07
     similares
    0.07
     "'
    0.07
     allerede
    0.07
     ранее
    0.06
     previamente
    0.06
    Activations Density 0.059%

    No Known Activations