© 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. 24893
    Prev
    Next
    INDEX
    Explanations

    instances of phrases that imply the presence of algebraic structures or entities

    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
    Šaltiniai
    -0.63
    potranspiration
    -0.57
     Pelleg
    -0.53
    AnchorTagHelper
    -0.51
    ló
    -0.50
    WRITER
    -0.48
    alds
    -0.48
     an
    -0.48
    ärzt
    -0.47
    žený
    -0.47
    POSITIVE LOGITS
    GOTREF
    0.76
     Cato
    0.72
    rrggbb
    0.72
    脚注の使い方
    0.60
    foreach
    0.60
    ⑨
    0.60
    ThroughAttribute
    0.59
    Rhestr
    0.58
     DAP
    0.58
     Roskov
    0.58
    Activations Density 0.023%

    No Known Activations