© 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. 1-RES-MATRYOSHKA-DC
    7. 1372
    Prev
    Next
    INDEX
    Explanations

    instances of the word "multiple" within a text

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    +#+#
    -0.80
    ArgsConstructor
    -0.66
    هر
    -0.59
    IntoConstraints
    -0.55
    一言
    -0.53
    DrawerToggle
    -0.53
     GetEnumerator
    -0.52
     ugu
    -0.51
     same
    -0.50
    ///</
    -0.50
    POSITIVE LOGITS
     multiple
    4.22
    multiple
    3.98
    Multiple
    3.94
     Multiple
    3.89
     MULTIPLE
    3.63
    MULTIPLE
    3.11
     múltiples
    2.63
     multiples
    2.47
     múltip
    2.33
     meerdere
    2.31
    Activations Density 0.214%

    No Known Activations