© 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-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29724
    Prev
    Next
    INDEX
    Explanations

    the word "compression"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.89
    ))
    -0.79
    ⓧ
    -0.69
    "))
    -0.69
    glUniform
    -0.69
     setuptools
    -0.69
    nament
    -0.68
    ")){
    -0.67
    ]:
    -0.67
    =""/>
    -0.66
    POSITIVE LOGITS
     compressors
    1.13
     compress
    1.02
     compres
    1.02
     Compression
    1.00
     compression
    0.96
     kompres
    0.96
     compressor
    0.95
     compressed
    0.89
     Compressed
    0.88
    Compress
    0.87
    Activations Density 0.004%

    No Known Activations