© 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. 4-CLT-HP
    7. 2612
    Prev
    Next
    INDEX
    Explanations

    followed

    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
    InvalidProtocol
    -0.81
    ReusableCell
    -0.75
    oa̍t
    -0.70
    ibatis
    -0.69
    TypedDataSet
    -0.69
    ergies
    -0.69
     hydrostatic
    -0.67
     revocation
    -0.66
    cokinetics
    -0.66
     pharmacological
    -0.65
    POSITIVE LOGITS
     by
    0.74
     Any
    0.48
     By
    0.46
     continúas
    0.45
     oleh
    0.43
    Any
    0.41
     immediately
    0.40
     двумя
    0.40
     всеми
    0.39
    any
    0.38
    Activations Density 0.005%

    No Known Activations