© 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. 1-RES-MATRYOSHKA-DC
    7. 408
    Prev
    Next
    INDEX
    Explanations

    references to specific computational or methodological approaches

    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
     وسی
    -0.52
    ContentLoaded
    -0.49
    lismo
    -0.48
    /**
    -0.48
    Legend
    -0.47
     resultCode
    -0.47
    Legends
    -0.47
     layui
    -0.47
    ゆ
    -0.46
    Liter
    -0.46
    POSITIVE LOGITS
     approach
    3.67
     Approach
    3.52
     APPROACH
    3.42
     approaches
    3.41
    approach
    3.38
    Approach
    3.30
     Approaches
    3.20
     approached
    3.02
     approaching
    2.80
     approche
    2.73
    Activations Density 1.471%

    No Known Activations