Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30309
    Prev
    Next
    INDEX
    Explanations

    the word "After" and words immediately after "After"

    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
     peor
    -0.56
     digitais
    -0.56
    ItemLayout
    -0.52
     Maguire
    -0.51
    ibatis
    -0.50
     späteren
    -0.50
    uresti
    -0.48
     dzięki
    -0.48
     kematian
    -0.48
     aplicar
    -0.48
    POSITIVE LOGITS
     myſelf
    0.80
    expandindo
    0.79
     AssemblyCulture
    0.76
     initComponents
    0.75
     Audiodateien
    0.75
    \{\\
    0.74
    NUMX
    0.74
     Houſe
    0.72
     المعيارى
    0.72
     itſelf
    0.70
    Activations Density 0.025%

    No Known Activations