© 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. 4772
    Prev
    Next
    INDEX
    Explanations

    references to vacuum pressure measurement

    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
    Δείτε
    -0.56
    CodeAttribute
    -0.54
    IntoConstraints
    -0.53
     queima
    -0.52
     sunburn
    -0.52
     myndig
    -0.52
    Vii
    -0.51
     Sagrada
    -0.50
    ומית
    -0.50
    roffenen
    -0.47
    POSITIVE LOGITS
     vacuum
    3.45
    vacuum
    3.09
     Vacuum
    3.05
    Vacuum
    2.88
     vacu
    2.19
    真空
    2.09
     vac
    1.81
    UUM
    1.70
     VAC
    1.50
     Vac
    1.48
    Activations Density 0.040%

    No Known Activations