© 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. 10631
    Prev
    Next
    INDEX
    Explanations

    references to nozzle parts in a manufacturing context

    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
     Alec
    -0.71
    Alec
    -0.63
    ⓧ
    -0.62
    Sent
    -0.60
    ":[{
    -0.59
     bieg
    -0.59
     piscinas
    -0.59
     Borg
    -0.58
    GLOBALS
    -0.58
     caminhada
    -0.58
    POSITIVE LOGITS
     nozzles
    1.80
     Nozzle
    1.79
     nozzle
    1.73
    zzles
    1.14
    zzle
    1.07
    ZZLE
    0.80
    letoe
    0.75
    ValueStyle
    0.74
    zzel
    0.73
    noz
    0.73
    Activations Density 0.003%

    No Known Activations