© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5569
    Prev
    Next
    INDEX
    Explanations

    the word "Por" in Spanish, indicating it's looking for the Spanish word "Por"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     JADX
    -0.74
    agisse
    -0.69
    mbic
    -0.66
     näky
    -0.65
    Hauptartikel
    -0.64
    mybatisplus
    -0.63
    Hermoso
    -0.63
    unnitel
    -0.62
     Erl
    -0.60
    älde
    -0.59
    POSITIVE LOGITS
     por
    2.94
     Por
    2.81
    Por
    2.78
    por
    2.59
     POR
    2.22
    POR
    2.06
    opor
    1.38
     poros
    1.30
     porosity
    1.21
     porc
    1.21
    Activations Density 0.094%

    No Known Activations