© 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. 9078
    Prev
    Next
    INDEX
    Explanations

    specific structural components and relationships in technical descriptions, particularly in engineering or scientific 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
    tempor
    -0.53
    cilla
    -0.50
    roek
    -0.46
    ViewChild
    -0.45
    Joueur
    -0.45
    teil
    -0.44
    espé
    -0.44
    kiri
    -0.44
    博物
    -0.44
    von
    -0.41
    POSITIVE LOGITS
    sizeCache
    0.82
    Personensuche
    0.75
     AssemblyCulture
    0.71
    UnusedPrivate
    0.71
    DebuggerNonUser
    0.71
    PerformLayout
    0.71
     للاسماء
    0.71
     utafitiHapana
    0.64
    mybatisplus
    0.64
    URBANA
    0.63
    Activations Density 0.252%

    No Known Activations