© 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. 13836
    Prev
    Next
    INDEX
    Explanations

    references to insensitive or rude behaviors

    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
    +:+
    -0.66
     препратки
    -0.63
     memoized
    -0.62
    ⎩
    -0.59
    ​=
    -0.57
    findpost
    -0.57
    Portail
    -0.57
     doInBackground
    -0.56
    WriteBarrier
    -0.56
     moindre
    -0.55
    POSITIVE LOGITS
     insensitive
    1.08
    aglia
    0.98
    insensitive
    0.93
     resuscitation
    0.76
     Raw
    0.70
    ardt
    0.67
     nematodes
    0.66
    parentNode
    0.65
     Norris
    0.65
    phological
    0.65
    Activations Density 0.028%

    No Known Activations