© 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. 5-CLT-HP
    7. 2658
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    Rohy
    -0.55
     Dernière
    -0.52
    威
    -0.48
    هم
    -0.45
    ally
    -0.45
    Identyfik
    -0.45
     currently
    -0.44
     Kle
    -0.44
     یاد
    -0.44
     au
    -0.44
    POSITIVE LOGITS
     مشين
    0.69
    脚注の使い方
    0.60
    corder
    0.59
    \{\\
    0.58
     الحره
    0.57
    徊
    0.56
    addContainerGap
    0.54
     élector
    0.54
     abbandon
    0.53
     שוליים
    0.52
    Activations Density 0.001%

    No Known Activations