© 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. 5489
    Prev
    Next
    INDEX
    Explanations

    mentions of issues or problems related to encountering or dealing with something

    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
    Française
    -0.76
     ModelExpression
    -0.73
    Portály
    -0.69
    Portail
    -0.68
    ArrowToggle
    -0.65
     चीज़ों
    -0.63
    :✨
    -0.62
     makeStyles
    -0.62
    useState
    -0.62
    NgModule
    -0.61
    POSITIVE LOGITS
     encountered
    2.67
     encounter
    2.58
    encounter
    2.58
     encounters
    2.50
     Encounter
    2.41
    Encounter
    2.30
     encountering
    2.16
     Encounters
    2.00
     Begegn
    1.38
     rencontr
    1.28
    Activations Density 0.007%

    No Known Activations