© 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. 17120
    Prev
    Next
    INDEX
    Explanations

    words related to propellants and chemicals

    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
    '])){
    -0.92
    Hozzáférés
    -0.85
     quý
    -0.80
    stateProvider
    -0.79
    SAI
    -0.77
    ليج
    -0.76
    NamedQueries
    -0.75
    sinx
    -0.74
    cemia
    -0.73
    isela
    -0.73
    POSITIVE LOGITS
    prop
    1.20
     Prop
    1.20
     prop
    1.20
    Prop
    1.05
     propeller
    1.05
     PROP
    1.02
    PROP
    0.89
     props
    0.84
     Props
    0.84
    PropTypes
    0.81
    Activations Density 0.006%

    No Known Activations