© 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. 5848
    Prev
    Next
    INDEX
    Explanations

    references to mechanical stress and strain, especially tensional stress

    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
    KommentareTeilen
    -0.90
    ftagPool
    -0.85
    Filmographie
    -0.77
     propOrder
    -0.72
    endphp
    -0.72
    MENAFN
    -0.71
    ьаж
    -0.69
     presses
    -0.68
     webdriver
    -0.67
     MotionEvent
    -0.66
    POSITIVE LOGITS
     tension
    3.31
     Tension
    3.03
    Tension
    2.84
    tension
    2.67
     tensions
    2.30
     tensión
    1.96
     tensione
    1.73
     tensão
    1.69
     tense
    1.52
    ENSION
    1.27
    Activations Density 0.006%

    No Known Activations