© 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. 8-RES-MATRYOSHKA-DC
    7. 29869
    Prev
    Next
    INDEX
    Explanations

    statements about results, particularly ones using the word "that"

    oai_token-act-pair · gemini-2.0-flash
    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
     Monfieur
    -0.77
     pleaſure
    -0.73
     myſelf
    -0.69
     iſt
    -0.68
     ſon
    -0.68
     perfons
    -0.66
     poul
    -0.65
     reaſon
    -0.65
    edenken
    -0.63
     Fins
    -0.63
    POSITIVE LOGITS
    XmlAccessorType
    0.66
    Personendaten
    0.65
     disambiguazione
    0.63
     wireType
    0.61
      
    0.59
     was
    0.56
    SpringRunner
    0.56
    تقاوى
    0.55
     had
    0.54
     seemed
    0.51
    Activations Density 0.224%

    No Known Activations