© 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. 0-RES-MATRYOSHKA-DC
    7. 11011
    Prev
    Next
    INDEX
    Explanations

    references to the word "orthogonal" or related terminology

    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
     AssemblyCulture
    -0.88
    
    -0.73
    djangoproject
    -0.69
    Lähteet
    -0.64
    jsdelivr
    -0.63
    gnore
    -0.63
    adone
    -0.63
     mouseY
    -0.62
    CodedInputStream
    -0.60
    iyle
    -0.59
    POSITIVE LOGITS
    ís
    1.09
    Pro
    0.78
     Joan
    0.67
    orth
    0.66
     proceeds
    0.64
    Joan
    0.58
    Personensuche
    0.57
    ERIE
    0.56
     boa
    0.55
    exitRule
    0.53
    Activations Density 0.004%

    No Known Activations