© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5187
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "the majority of" or "most" objects or quantities

    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
    abello
    -0.76
    verarbeitung
    -0.70
     userRepository
    -0.68
     useRef
    -0.66
    ChildScrollView
    -0.66
     AssemblyCulture
    -0.65
    FirebaseDatabase
    -0.62
    enterOuterAlt
    -0.62
    ſten
    -0.61
    blurRadius
    -0.61
    POSITIVE LOGITS
     los
    0.91
    Οι
    0.87
     οι
    0.82
     les
    0.77
     των
    0.74
     mga
    0.70
    Los
    0.69
     Οι
    0.68
     las
    0.67
     các
    0.65
    Activations Density 0.036%

    No Known Activations