© 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. 130966
    Prev
    Next
    INDEX
    Explanations

    merge and combine data

    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
    해야
    -0.06
    验证
    -0.06
     deo
    -0.06
     flirt
    -0.06
     NUE
    -0.06
    🎢
    -0.06
     نئے
    -0.06
    峨
    -0.05
     föränd
    -0.05
     NSURL
    -0.05
    POSITIVE LOGITS
    รวม
    0.07
     campuran
    0.07
    เพิ่มเติม
    0.07
     transferencia
    0.07
     Additional
    0.07
     merging
    0.06
     merge
    0.06
    枃
    0.06
     loosely
    0.06
     merged
    0.06
    Activations Density 0.004%

    No Known Activations