© 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. 15786
    Prev
    Next
    INDEX
    Explanations

    terms related to scaffolding in biological contexts

    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
     Caron
    -0.78
     Finley
    -0.77
     tristesse
    -0.77
    الإنجليزية
    -0.73
     Sonnen
    -0.72
    preso
    -0.70
    Stones
    -0.69
    Wesley
    -0.68
    Referências
    -0.67
     irons
    -0.66
    POSITIVE LOGITS
     scaffold
    1.59
     scaffolds
    1.54
    scaffold
    1.46
    sca
    1.42
    Sca
    1.37
     Sca
    1.30
     Scaffold
    1.28
     scaff
    1.27
     scaffolding
    1.25
    Scaffold
    1.16
    Activations Density 0.007%

    No Known Activations