© 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. 0-CLT-HP
    7. 38426
    Prev
    Next
    INDEX
    Explanations

    used

    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
     used
    -1.83
    Used
    -1.43
    used
    -1.38
     Used
    -1.34
     uſed
    -1.23
     USED
    -1.18
     utilisé
    -1.14
     digunakan
    -1.10
     usado
    -1.10
     utilizado
    -1.09
    POSITIVE LOGITS
     the
    0.76
     a
    0.65
     an
    0.59
    دانشنامهٔ
    0.57
    الحياه
    0.55
     it
    0.54
     ‘
    0.52
    showthread
    0.50
     them
    0.48
     것이
    0.48
    Activations Density 0.040%

    No Known Activations