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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-RES-MATRYOSHKA-DC
    4. 763
    Prev
    Next
    INDEX
    Explanations

    references to gene expression levels

    oai_token-act-pair · gpt-4.1-nano
    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
    ex
    -1.49
     Ex
    -1.40
    Ex
    -1.36
     ex
    -1.30
    EX
    -1.20
     EX
    -1.07
     exon
    -1.01
     éx
    -1.00
     exe
    -0.95
     Exe
    -0.93
    POSITIVE LOGITS
     expression
    2.86
     Expression
    2.55
    expression
    2.44
     expressions
    2.34
    Expression
    2.22
     Expressions
    2.05
     expresión
    1.97
     expressão
    1.95
    expressions
    1.80
    Expressions
    1.66
    Activations Density 0.257%

    No Known Activations