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. 97975
    Prev
    Next
    INDEX
    Explanations

    Cube

    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
     myſelf
    -1.13
     itſelf
    -0.94
     himſelf
    -0.94
    ſelves
    -0.90
     themſelves
    -0.90
     Efq
    -0.88
     quran
    -0.87
     greateſt
    -0.87
     leſs
    -0.87
     pleaſure
    -0.87
    POSITIVE LOGITS
     Mar
    0.73
    .
    0.71
     
    0.70
    ,
    0.67
    Mar
    0.66
    -
    0.66
     Mal
    0.65
    el
    0.63
     K
    0.62
     Kar
    0.61
    Activations Density 0.069%

    No Known Activations