© 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. 5558
    Prev
    Next
    INDEX
    Explanations

    references to actions involving change or simulation procedures

    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
     quidem
    -0.54
    hikari
    -0.52
    TabStop
    -0.52
    벳
    -0.51
    揄
    -0.50
    로그램
    -0.48
    rishnan
    -0.47
    ष्य
    -0.47
    ScreenState
    -0.47
     Programm
    -0.47
    POSITIVE LOGITS
    TypedDataSet
    1.05
    RenderAtEndOf
    0.81
     Савезне
    0.79
     ModelExpression
    0.78
     propOrder
    0.76
    ISupport
    0.73
    GEBURTSDATUM
    0.71
     nahilalakip
    0.71
    noopener
    0.71
    تقاوى
    0.68
    Activations Density 1.842%

    No Known Activations