© 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. 17341
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fluid."

    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
    liquid
    -0.73
     líqu
    -0.72
     market
    -0.70
    Liquid
    -0.70
     LIQUID
    -0.70
     Hager
    -0.69
     Ke
    -0.66
     Schae
    -0.65
     капи
    -0.65
     Olsson
    -0.65
    POSITIVE LOGITS
     Fluid
    1.11
     Fluids
    1.05
     fluids
    1.02
     fluid
    0.99
    Fluid
    0.97
     FLUID
    0.96
     Avid
    0.89
     SAX
    0.88
    fluid
    0.87
     FLAC
    0.81
    Activations Density 0.008%

    No Known Activations