© 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. 13759
    Prev
    Next
    INDEX
    Explanations

    expressions of affirmation or affirmation-related language

    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
     itſelf
    -1.19
     ſever
    -1.02
     myſelf
    -1.01
     pleaſure
    -0.98
     ſche
    -0.97
     ſmall
    -0.96
     Monfieur
    -0.96
     raiſ
    -0.95
     Diſ
    -0.94
     Houſe
    -0.94
    POSITIVE LOGITS
     li
    0.61
     null
    0.54
     Mar
    0.53
     di
    0.53
     gj
    0.53
     Di
    0.52
     c
    0.51
     de
    0.51
     “
    0.51
     ab
    0.51
    Activations Density 0.189%

    No Known Activations