© 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. 130946
    Prev
    Next
    INDEX
    Explanations

    was / see / ever / used / you / have / significant / there

    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
     is
    -0.09
     has
    -0.07
    にとって
    -0.06
     enable
    -0.06
     can
    -0.06
     চূড়ান্ত
    -0.06
     जोश
    -0.06
     sowohl
    -0.06
     from
    -0.06
     would
    -0.06
    POSITIVE LOGITS
     Schuld
    0.06
    类似于
    0.06
    engaruhi
    0.06
    ৃতা
    0.06
     similaires
    0.06
    暂时
    0.06
    imageId
    0.06
     অঞ্চলে
    0.06
     防止
    0.06
    特別な
    0.06
    Activations Density 0.009%

    No Known Activations