© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43456
    Prev
    Next
    INDEX
    Explanations

    much

    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
     much
    -2.41
    much
    -2.28
    Much
    -2.23
     Much
    -2.06
     MUCH
    -1.61
     mucho
    -1.46
     paljon
    -1.23
     beaucoup
    -1.21
     mye
    -1.13
     mycket
    -1.12
    POSITIVE LOGITS
    出版年
    0.66
     of
    0.57
    leqq
    0.54
    ่านั้น
    0.53
    Obrázky
    0.52
    Ucraina
    0.52
     further
    0.51
     relâche
    0.49
    antaine
    0.49
     shall
    0.49
    Activations Density 0.040%

    No Known Activations