© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13454
    Prev
    Next
    INDEX
    Explanations

    action words indicating the act of arriving or reaching a particular state or position

    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
     taken
    -0.66
     chosen
    -0.63
    Taken
    -0.57
     Taken
    -0.57
     beaten
    -0.56
    chosen
    -0.54
     driven
    -0.53
    充足
    -0.52
     Driven
    -0.50
    taken
    -0.47
    POSITIVE LOGITS
    PerformLayout
    1.14
     bezeichneter
    0.85
    참고
    0.82
    RenderAtEndOf
    0.79
    ScopeManager
    0.79
    AutoresizingMask
    0.79
    脚注の使い方
    0.76
     doInBackground
    0.76
    AnchorStyles
    0.75
    woordig
    0.73
    Activations Density 0.005%

    No Known Activations