© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73709
    Prev
    Next
    INDEX
    Explanations

    Technical/code snippets

    np_max-act-logits · 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
    GEBURTSDATUM
    -0.91
    enderror
    -0.84
     مشين
    -0.82
    IsContent
    -0.80
    Gön
    -0.77
     صوتيه
    -0.75
    ArrowToggle
    -0.73
     '\\;'
    -0.71
     استنادى
    -0.71
    gain
    -0.70
    POSITIVE LOGITS
    櫥
    0.38
    UserContext
    0.34
     Sucher
    0.34
    CHD
    0.34
    Unmarshaller
    0.34
    сме
    0.33
    ostasis
    0.33
     berço
    0.32
    chauffer
    0.32
    مئ
    0.31
    Activations Density 0.000%

    No Known Activations