© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 131070
    Prev
    Next
    INDEX
    Explanations

    Hashing, character identifiers

    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
     the
    -0.06
    very
    -0.06
     enormously
    -0.06
    ごとに
    -0.06
                         
    -0.06
    だけ
    -0.06
    幅
    -0.05
                        
    -0.05
                           
    -0.05
    <0x89>
    -0.05
    POSITIVE LOGITS
     doesnt
    0.07
     nacido
    0.06
     funcao
    0.06
    冷静
    0.06
     hason
    0.06
     بسبب
    0.06
     owing
    0.06
     alrededores
    0.06
     একটি
    0.06
     दोनों
    0.06
    Activations Density 0.010%

    No Known Activations