© 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. 3249
    Prev
    Next
    INDEX
    Explanations

    the word "Mal" in various contexts

    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
     tué
    -0.72
     Clermont
    -0.70
     NUnit
    -0.70
     Upan
    -0.66
     Buc
    -0.65
    SuppressLint
    -0.65
     quæ
    -0.64
     ujednoznacz
    -0.64
     igång
    -0.63
     détruit
    -0.62
    POSITIVE LOGITS
     Mal
    3.53
    Mal
    3.47
     mal
    3.20
    mal
    3.02
     MAL
    2.92
    MAL
    2.78
     Malt
    1.71
     Malcolm
    1.62
     malt
    1.62
    mali
    1.62
    Activations Density 0.028%

    No Known Activations