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. 20-CLT-HP
    4. 74735
    Prev
    Next
    INDEX
    Explanations

    technical snippets and words

    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
     jan
    -0.39
    LICENSE
    -0.39
     везе
    -0.39
    лізу
    -0.37
    diye
    -0.37
     sprung
    -0.36
    extAlignment
    -0.35
     leger
    -0.35
     Lum
    -0.35
     taco
    -0.35
    POSITIVE LOGITS
    WriteBarrier
    0.77
    ########.
    0.72
    RegressionTest
    0.70
     autorytatywna
    0.62
     Scribd
    0.61
     aeruginosa
    0.60
     Мексичка
    0.60
     présidentielle
    0.60
    PreExecute
    0.59
    ništvo
    0.59
    Activations Density 0.001%

    No Known Activations