© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26526
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "flux" in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Odon
    -0.75
    mfenced
    -0.73
    AddAttribute
    -0.73
     Pomer
    -0.71
     pomer
    -0.71
    Reprodu
    -0.70
     Rudi
    -0.68
    Grig
    -0.68
     Moun
    -0.67
     Havel
    -0.67
    POSITIVE LOGITS
     flux
    1.88
     Flux
    1.77
     fluxes
    1.72
    flux
    1.66
    Flux
    1.66
    lux
    0.95
    AddTagHelper
    0.89
     flujo
    0.84
    Cordialement
    0.77
    BoxShadow
    0.77
    Activations Density 0.004%

    No Known Activations