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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 712
    Prev
    Next
    INDEX
    Explanations

    reliable

    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
    reliable
    -0.95
    Reliable
    -0.87
     reliable
    -0.87
     dependable
    -0.82
    liability
    -0.81
     unreliable
    -0.80
     Reliable
    -0.75
     reliability
    -0.72
    liable
    -0.71
    MERCIAL
    -0.66
    POSITIVE LOGITS
     مشين
    0.60
    الحياه
    0.56
    GetEnumerator
    0.40
     programmi
    0.40
    جستارهای
    0.40
    Literatur
    0.40
    BeginInit
    0.39
     étro
    0.39
    jant
    0.38
     rotación
    0.38
    Activations Density 0.028%

    No Known Activations