© 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. 9514
    Prev
    Next
    INDEX
    Explanations

    occurrences of the "Override" annotation in code

    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
    abestanden
    -0.81
     ویکی‌پدیای
    -0.81
    Bibliograf
    -0.79
     ligiloj
    -0.79
     فريبيس
    -0.76
    cèse
    -0.74
     AssemblyCulture
    -0.66
    tagHelperRunner
    -0.66
    desert
    -0.65
    PreExecute
    -0.63
    POSITIVE LOGITS
    Override
    1.39
    MockBean
    0.53
     strict
    0.51
    esai
    0.50
     Sputnik
    0.50
    OCCURRED
    0.50
    ↵
    0.49
     AspNetCore
    0.49
    ArgsConstructor
    0.48
     eins
    0.48
    Activations Density 0.002%

    No Known Activations