© 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. 45048
    Prev
    Next
    INDEX
    Explanations

    technical/scientific context

    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
     Wille
    -1.01
     Mifflin
    -0.97
     חיצוניים
    -0.73
    borderSide
    -0.71
    skjaer
    -0.68
     Palais
    -0.65
    BufferException
    -0.62
    aarrggbb
    -0.61
     EnglishChoose
    -0.61
    rrggbb
    -0.60
    POSITIVE LOGITS
    kops
    0.47
    ρεί
    0.45
    perl
    0.45
    üste
    0.45
     الرحمن
    0.44
    Batis
    0.44
    ||}
    0.41
    buie
    0.41
    brun
    0.41
    bois
    0.41
    Activations Density 0.161%

    No Known Activations