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. 0-CLT-HP
    4. 696
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.24
     itſelf
    -1.03
     Monfieur
    -1.00
     auffi
    -0.99
     pleaſure
    -0.96
     ainfi
    -0.95
     vectorstock
    -0.94
     becauſe
    -0.93
     iſt
    -0.92
     Jefus
    -0.92
    POSITIVE LOGITS
    .
    0.94
    -
    0.87
    ,
    0.82
     (
    0.77
     ‘
    0.77
     “
    0.75
     –
    0.74
    ’
    0.74
    ↵
    0.73
     s
    0.73
    Activations Density 0.380%

    No Known Activations