© 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. 2-RES-MATRYOSHKA-DC
    7. 2981
    Prev
    Next
    INDEX
    Explanations

    references to digital or digital-related concepts

    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
     horseshoe
    -0.56
    enig
    -0.53
     digits
    -0.52
     Nightmare
    -0.52
    러나
    -0.51
     Susana
    -0.51
    angliski
    -0.51
     conf
    -0.51
    opardy
    -0.50
     τρο
    -0.50
    POSITIVE LOGITS
     digital
    2.61
     Digital
    2.58
    Digital
    2.56
    digital
    2.48
     DIGITAL
    2.33
    DIGITAL
    2.33
     digitales
    2.05
     digitally
    1.92
     digitale
    1.91
     digitais
    1.74
    Activations Density 0.058%

    No Known Activations