© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1245
    Prev
    Next
    INDEX
    Explanations

    have

    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
    tagHelperRunner
    -0.70
     للمعارف
    -0.66
     >=",
    -0.65
     surla
    -0.65
    RegistryLite
    -0.60
    ItemBackground
    -0.57
     CommonModule
    -0.55
     wiedzieć
    -0.54
     {}));
    -0.53
    modelBuilder
    -0.51
    POSITIVE LOGITS
     to
    0.95
     simplifié
    0.49
    ecutable
    0.49
    ført
    0.49
    belanja
    0.48
    INGO
    0.47
    LEGGI
    0.46
     catal
    0.46
    Bibliograf
    0.46
    γχ
    0.45
    Activations Density 0.181%

    No Known Activations