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. 5-CLT-HP
    4. 95544
    Prev
    Next
    INDEX
    Explanations

    store

    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
    ImageContext
    -0.84
    aarrggbb
    -0.72
    HtmlAttribute
    -0.71
     насељу
    -0.71
    richTextPanel
    -0.69
    PerformLayout
    -0.68
     hysteresis
    -0.65
     adjuster
    -0.63
     Mitigation
    -0.61
     Contamin
    -0.61
    POSITIVE LOGITS
     last
    0.56
     Last
    0.52
     oublier
    0.46
    Last
    0.46
    hatsu
    0.43
    .${
    0.43
    English
    0.41
     &___
    0.41
     /\.(
    0.40
     ultimi
    0.40
    Activations Density 0.975%

    No Known Activations