© 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. 23600
    Prev
    Next
    INDEX
    Explanations

    phrasings that refer to time and events in relation to conditions or changes

    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
    )_/¯
    -0.56
    )");
    -0.56
    yscy
    -0.55
    endgroup
    -0.52
     redund
    -0.50
    $.}
    -0.50
    </tfoot>
    -0.49
    éta
    -0.48
    IEWS
    -0.48
    interopRequire
    -0.48
    POSITIVE LOGITS
    AxisAlignment
    0.74
    sizeCache
    0.63
     vallen
    0.60
    Geplaatst
    0.60
    NameInMap
    0.58
     Reign
    0.58
    protoimpl
    0.56
    Espèce
    0.56
    PropertyChanging
    0.55
    DllImport
    0.54
    Activations Density 0.061%

    No Known Activations