© 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. 5065
    Prev
    Next
    INDEX
    Explanations

    references to the process of molecular or structural relaxation in materials science

    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
    hyrchwyd
    -0.95
    OGND
    -0.83
     оригіналу
    -0.79
     &___
    -0.76
     Schindler
    -0.71
     himo
    -0.70
    minecraftforge
    -0.70
    InjectAttribute
    -0.69
    setVerticalGroup
    -0.69
    AddAttribute
    -0.68
    POSITIVE LOGITS
    relax
    3.02
     relax
    2.98
     relaxation
    2.98
    Relax
    2.88
     Relax
    2.78
     Relaxation
    2.67
     relaxes
    2.67
     relaxed
    2.61
     relaxing
    2.58
    relaxed
    2.27
    Activations Density 0.016%

    No Known Activations