© 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. 3116
    Prev
    Next
    INDEX
    Explanations

    the prepositions "za", "u", "na", and "s" which mean "for/from", "in", "on", and "with", respectively - it appears to be detecting a Slavic language

    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
    Not in Any Lists

    No Comments

    Negative Logits
    อย่างไร
    -0.56
    TokenNameLBRACE
    -0.56
     которого
    -0.54
     linkovi
    -0.54
    lapsingToolbar
    -0.54
    nextProps
    -0.53
    rawdę
    -0.52
     وتسجيلات
    -0.52
    的行
    -0.52
     Phipps
    -0.51
    POSITIVE LOGITS
     за
    0.99
     к
    0.89
     с
    0.88
     у
    0.88
     о
    0.84
    ůli
    0.83
     при
    0.81
    При
    0.75
     по
    0.75
    За
    0.73
    Activations Density 0.063%

    No Known Activations