© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3376
    Prev
    Next
    INDEX
    Explanations

    the word "up"

    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
    Negative Logits
    InjectAttribute
    -1.02
    Datuak
    -0.66
    +:+
    -0.66
    leukin
    -0.66
    ParallelGroup
    -0.66
    Swish
    -0.61
    XmlAttribute
    -0.60
    phrine
    -0.60
    USTAIN
    -0.59
     WaitForSeconds
    -0.58
    POSITIVE LOGITS
    FormTagHelper
    0.58
    fortawesome
    0.57
    ysl
    0.53
    chnet
    0.52
    lization
    0.51
    DoubleQuotes
    0.50
    writeFieldEnd
    0.50
     pij
    0.50
    ErrUnexpectedEOF
    0.50
    setVerticalGroup
    0.49
    Activations Density 0.079%

    No Known Activations