© 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. 15433
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis or pointing out a specific element

    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
     ceci
    -0.65
     Winaray
    -0.65
     MAYO
    -0.64
    Personensuche
    -0.62
     saites
    -0.60
    IntoConstraints
    -0.60
    intahan
    -0.58
    DataSetChanged
    -0.57
    dyž
    -0.57
     = 
    -0.54
    POSITIVE LOGITS
     esse
    2.98
     essa
    2.38
     Esse
    2.25
    Esse
    2.16
     desse
    1.81
     nesse
    1.78
     Ese
    1.62
    Ese
    1.59
    Essa
    1.55
     Essa
    1.55
    Activations Density 0.001%

    No Known Activations