© 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. 6122
    Prev
    Next
    INDEX
    Explanations

    references to liquid and liquid crystal materials

    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
    Negative Logits
     Stowe
    -0.72
     freckles
    -0.70
     fotográfico
    -0.69
    makeConstraints
    -0.68
     photosynthesis
    -0.66
     scales
    -0.64
     Birken
    -0.63
     GenerationType
    -0.61
     paro
    -0.60
    ]")]
    -0.60
    POSITIVE LOGITS
    QUID
    1.19
     Liquid
    1.16
    Liquid
    1.16
     LIQUID
    1.16
     FLUID
    1.14
    liquid
    1.13
     liquid
    1.12
    quid
    1.10
     Fluids
    1.10
     Fluid
    1.09
    Activations Density 0.034%

    No Known Activations