© 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. 97565
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     intrusion
    -0.69
     intr
    -0.57
     intrusions
    -0.55
     intruder
    -0.51
     Article
    -0.50
    react
    -0.48
    re
    -0.45
     menyus
    -0.45
     Intru
    -0.44
     tutela
    -0.44
    POSITIVE LOGITS
    NOPQRST
    0.96
    protoimpl
    0.85
     propOrder
    0.77
    клопе
    0.76
    TargetException
    0.72
    msgSender
    0.70
    addCriterion
    0.65
    TintMode
    0.65
    دانشنامهٔ
    0.64
    UMBIA
    0.64
    Activations Density 0.315%

    No Known Activations