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. 11216
    Prev
    Next
    INDEX
    Explanations

    cin

    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
    Gön
    -0.80
     autorytatywna
    -0.71
    tableFuture
    -0.69
    Geplaatst
    -0.66
     Ngb
    -0.65
    <!--[
    -0.64
    resave
    -0.64
     financeiro
    -0.62
     sentiers
    -0.62
    WaitGroup
    -0.62
    POSITIVE LOGITS
     J
    0.46
    ∑
    0.42
     nonatomic
    0.42
    Map
    0.41
     Nas
    0.41
    Os
    0.41
     ante
    0.41
    lüssel
    0.40
     alias
    0.39
    degree
    0.39
    Activations Density 0.030%

    No Known Activations