© 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. 0-RES-MATRYOSHKA-DC
    7. 12736
    Prev
    Next
    INDEX
    Explanations

    references to involuntary or unintended events or actions

    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
    ordning
    -0.62
     fome
    -0.62
     Experimental
    -0.58
     éc
    -0.57
     thefe
    -0.57
    Enllaços
    -0.57
     industriel
    -0.57
    EXPERIMENTAL
    -0.56
    存于互联网档案馆
    -0.56
     insufficient
    -0.55
    POSITIVE LOGITS
     involuntary
    2.06
     involuntarily
    1.85
     unintentionally
    1.82
     unintended
    1.74
     unintentional
    1.66
     inadvert
    1.65
     unwittingly
    1.64
     inadvertently
    1.61
     involunt
    1.61
     unknowingly
    1.55
    Activations Density 0.002%

    No Known Activations