© 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. 3-RES-MATRYOSHKA-DC
    7. 3461
    Prev
    Next
    INDEX
    Explanations

    words like "any", "other", and "else" that could be used as part of superlative descriptions

    oai_token-act-pair · gemini-2.0-flash
    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
    ïti
    -0.64
     juste
    -0.59
    SequentialGroup
    -0.58
    triangleq
    -0.57
    XmlAccessType
    -0.56
    rungsseite
    -0.56
    เภ
    -0.55
    ValueStyle
    -0.53
     تانيه
    -0.52
    cé
    -0.51
    POSITIVE LOGITS
     greateſt
    0.62
    ToInt
    0.57
     eccell
    0.57
     beſt
    0.56
    SharedDtor
    0.54
     moft
    0.54
     najbol
    0.53
     houſe
    0.53
     `;
    0.53
    withstanding
    0.52
    Activations Density 0.207%

    No Known Activations