© 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. 31146
    Prev
    Next
    INDEX
    Explanations

    terms related to the properties and measurement of viscosity in substances

    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
    ArgsConstructor
    -0.67
     AssemblyProduct
    -0.67
     olímp
    -0.66
    InputBorder
    -0.66
     împre
    -0.62
     Pok
    -0.61
     iprot
    -0.61
     WaitForSeconds
    -0.61
     Popo
    -0.60
     alman
    -0.60
    POSITIVE LOGITS
     Viscosity
    1.48
     viscosity
    1.45
    Viscosity
    1.36
    vis
    1.18
    cosity
    1.15
     visco
    1.02
     viscous
    1.02
     Vis
    1.01
     vis
    0.92
    VIS
    0.92
    Activations Density 0.020%

    No Known Activations