© 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. 5-CLT-HP
    4. 134
    Prev
    Next
    INDEX
    Explanations

    similar

    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
    м
    -0.39
    Bata
    -0.38
     drying
    -0.38
    jem
    -0.37
    gra
    -0.37
    лно
    -0.37
     Jana
    -0.37
    ответ
    -0.36
     عام
    -0.36
    em
    -0.36
    POSITIVE LOGITS
     Normdatei
    0.73
     fubject
    0.69
     سكانية
    0.69
    principalColumn
    0.68
    tagext
    0.67
    ientôt
    0.66
    IntoConstraints
    0.66
     continúas
    0.65
    :✨
    0.65
    imbawa
    0.65
    Activations Density 0.528%

    No Known Activations