© 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. 18670
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical tests and analysis methods

    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
    amaged
    -0.65
    avice
    -0.64
     geldig
    -0.62
     cref
    -0.57
     Carden
    -0.57
     canes
    -0.52
    ^(@)
    -0.50
     distractions
    -0.49
    nalités
    -0.49
     createdAt
    -0.49
    POSITIVE LOGITS
     كومونز
    0.83
    AnchorTagHelper
    0.81
    +#+#
    0.79
    providedIn
    0.69
    存于互联网档案馆
    0.66
     ModelExpression
    0.65
    writeFieldEnd
    0.63
    DrawerToggle
    0.63
    WithIOException
    0.61
    Autoritní
    0.61
    Activations Density 0.007%

    No Known Activations