© 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. 5214
    Prev
    Next
    INDEX
    Explanations

    references to directly performing actions or operations

    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
    direct
    -1.00
     Direct
    -0.91
     direct
    -0.85
     directs
    -0.82
    anskje
    -0.71
     directing
    -0.68
     directed
    -0.67
     asimismo
    -0.67
    harusnya
    -0.61
    directed
    -0.61
    POSITIVE LOGITS
     directly
    2.08
    directly
    1.89
     Directly
    1.84
     directement
    1.57
     direttamente
    1.41
     directamente
    1.35
     diretamente
    1.32
     bezpośrednio
    1.20
     přímo
    1.05
     непосредственно
    1.02
    Activations Density 0.009%

    No Known Activations