© 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. 4347
    Prev
    Next
    INDEX
    Explanations

    references to legal or judicial actions involving the concept of supporting or maintaining 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
     وتسجيلات
    -0.93
     تضيفلها
    -0.87
     незавершена
    -0.86
     Wikimedijinoj
    -0.80
     TextAppearance
    -0.80
    ंदीखरीदारी
    -0.80
     travaillons
    -0.80
    cestry
    -0.78
     recensement
    -0.77
    BeforeEach
    -0.76
    POSITIVE LOGITS
    sustain
    2.73
     Sustain
    2.70
     sustained
    2.70
     sustain
    2.64
    Sustain
    2.59
     sustaining
    2.33
     SUSTAIN
    2.30
     sustains
    2.27
    sustaining
    1.89
     sustainable
    1.72
    Activations Density 0.010%

    No Known Activations