© 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. 7338
    Prev
    Next
    INDEX
    Explanations

    statements related to being told or informed

    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
    bibitem
    -0.54
     continúas
    -0.53
     poveznice
    -0.51
     mendukung
    -0.50
     memungkinkan
    -0.49
    ękuję
    -0.47
    available
    -0.47
     rada
    -0.47
     lay
    -0.47
    ształ
    -0.47
    POSITIVE LOGITS
    migrationBuilder
    0.84
    ScopeManager
    0.75
     nahilalakip
    0.66
    queryInterface
    0.65
    IUrlHelper
    0.60
     cherchés
    0.59
    UserScript
    0.59
     WaitForSeconds
    0.58
     Paglinawan
    0.57
     lục
    0.55
    Activations Density 0.419%

    No Known Activations