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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13901
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "which."

    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
    findpost
    -0.58
     createSlice
    -0.57
     onde
    -0.56
     where
    -0.56
    initComponents
    -0.55
     которые
    -0.55
     fale
    -0.50
     которых
    -0.50
    рс
    -0.49
     których
    -0.48
    POSITIVE LOGITS
     feroit
    0.82
     auroit
    0.77
     étoit
    0.77
     ainfi
    0.74
     étoient
    0.73
    mapStateToProps
    0.71
     pouvoit
    0.70
     bisous
    0.70
     avoient
    0.69
     ſeveral
    0.68
    Activations Density 0.121%

    No Known Activations