© 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. 5932
    Prev
    Next
    INDEX
    Explanations

    sequences of high-density block symbols used in formatting or layout

    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
       
    -0.51
      
    -0.50
        
    -0.50
     moment
    -0.47
    -0.45
    usione
    -0.44
    alk
    -0.41
     deletion
    -0.40
     you
    -0.40
     
    -0.39
    POSITIVE LOGITS
     estimés
    1.16
     AssemblyCulture
    1.08
    دانشنامهٔ
    1.08
     للمعارف
    1.03
    uxxxx
    0.94
    ftagPool
    0.90
    HasColumnType
    0.88
    DIPSETTING
    0.83
     AssemblyCompany
    0.82
    AddTagHelper
    0.82
    Activations Density 0.455%

    No Known Activations