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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13725
    Prev
    Next
    INDEX
    Explanations

    references to the word "pode" indicating ability or permission

    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
     saites
    -0.72
     voici
    -0.68
    jména
    -0.67
     gynhyrchwyd
    -0.63
     BIBSYS
    -0.61
    contentLoaded
    -0.60
     StatefulWidget
    -0.60
    Демографія
    -0.60
    حياته
    -0.60
     EoL
    -0.60
    POSITIVE LOGITS
     pode
    2.28
    Pode
    1.66
     Pode
    1.59
     puede
    1.50
     peut
    1.45
     podem
    1.41
     pueden
    1.37
     Puede
    1.19
     poate
    1.17
     può
    1.15
    Activations Density 0.003%

    No Known Activations