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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11190
    Prev
    Next
    INDEX
    Explanations

    Code/Software

    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
     Pi
    -0.65
     pi
    -0.61
    agascar
    -0.59
    pi
    -0.57
    pius
    -0.56
    saver
    -0.51
     الحره
    -0.50
     pip
    -0.49
    pip
    -0.49
    出来ます
    -0.48
    POSITIVE LOGITS
    findpost
    0.61
    Hozzáférés
    0.60
    MessageTagHelper
    0.52
    IntoConstraints
    0.52
     excru
    0.51
    Lip
    0.51
     Olympedia
    0.50
    /*:
    0.50
    EndProject
    0.49
     ligiloj
    0.49
    Activations Density 0.025%

    No Known Activations