© 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. 3-RES-MATRYOSHKA-DC
    7. 2339
    Prev
    Next
    INDEX
    Explanations

    references to geography, time, statistics and relationships

    oai_token-act-pair · gemini-2.0-flash
    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
     surla
    -0.82
    +#+#
    -0.72
    клопе
    -0.71
    Tikang
    -0.69
     betweenstory
    -0.68
    Rüyada
    -0.68
    发表于
    -0.67
     Roskov
    -0.65
    RegisterType
    -0.63
    ftagPool
    -0.63
    POSITIVE LOGITS
     countries
    0.59
    countries
    0.56
     mainland
    0.54
     onCreateView
    0.51
     Countries
    0.49
    stateProvider
    0.47
    Countries
    0.47
    허
    0.46
     Canada
    0.45
    PickerController
    0.45
    Activations Density 1.375%

    No Known Activations