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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73989
    Prev
    Next
    INDEX
    Explanations

    bad situations

    np_max-act-logits · 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
    expandindo
    -0.71
    IVEREF
    -0.56
     démocr
    -0.53
     dilaporkan
    -0.53
     bezeichneter
    -0.53
     cuillère
    -0.51
     StatefulWidget
    -0.50
     grossa
    -0.49
     feroit
    -0.49
    berdayakan
    -0.47
    POSITIVE LOGITS
     mess
    1.05
     nightmare
    0.92
     disaster
    0.90
     cess
    0.86
     monstros
    0.83
     abomination
    0.81
     hell
    0.81
     monster
    0.77
     catastrophe
    0.77
     mon
    0.75
    Activations Density 0.006%

    No Known Activations