© 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
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 920
    Prev
    Next
    INDEX
    Explanations

    references to the word "unit" and related technical specifications

    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
     nahilalakip
    -0.57
    arkov
    -0.55
     IndexPath
    -0.54
    Demografía
    -0.54
    VideoCapture
    -0.52
    Demografia
    -0.52
     JpaRepository
    -0.51
    GHIJKLM
    -0.51
    elski
    -0.51
     للمعارف
    -0.50
    POSITIVE LOGITS
     unit
    4.78
     Unit
    4.41
    unit
    4.31
    Unit
    4.25
     units
    4.16
     Units
    3.92
     UNIT
    3.86
    units
    3.63
    UNIT
    3.61
     UNITS
    3.42
    Activations Density 0.072%

    No Known Activations