© 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. 20381
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific processes and measurements in protein crystallization

    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
    urlopen
    -0.49
    تقاوى
    -0.47
    ISupport
    -0.44
    DebuggerNonUser
    -0.43
    nesto
    -0.43
    GEBURTS
    -0.43
    tispiece
    -0.43
    出版年
    -0.42
     ModelExpression
    -0.42
    filé
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.83
    AddHtmlAttribute
    0.75
    onViewCreated
    0.73
    AsUp
    0.73
     дописавши
    0.71
    elemField
    0.71
    ConstraintMaker
    0.70
     estimés
    0.70
     otomatig
    0.66
     InputDecoration
    0.66
    Activations Density 0.318%

    No Known Activations