© 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. 7305
    Prev
    Next
    INDEX
    Explanations

    references to the process of improving or increasing 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
    Growth
    -0.80
     growth
    -0.78
     Growth
    -0.77
    growth
    -0.69
     GROWTH
    -0.69
    archiw
    -0.65
     uParam
    -0.64
    первых
    -0.64
     grows
    -0.62
    Growing
    -0.60
    POSITIVE LOGITS
     enhancement
    2.22
     enhance
    2.05
     Enhancement
    2.03
     Enhance
    2.02
    enhance
    2.02
     enhancing
    2.00
    Enhance
    2.00
    enhanced
    1.91
     enhanced
    1.88
     Enhanced
    1.86
    Activations Density 0.023%

    No Known Activations