© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91940
    Prev
    Next
    INDEX
    Explanations

    peace

    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
    oa̍t
    -0.69
     Vikipedi
    -0.68
     Schreiber
    -0.59
    niająca
    -0.58
     Himo
    -0.57
    Personensuche
    -0.57
    Geografía
    -0.56
     correctes
    -0.56
     تضيفلها
    -0.56
     ویکی‌پدیا
    -0.56
    POSITIVE LOGITS
     of
    0.81
    of
    0.56
     interiores
    0.53
     intérieur
    0.51
     internos
    0.49
    NetworkInfo
    0.49
    ).__
    0.47
    tof
    0.47
    FileNotFound
    0.46
    bootstrapcdn
    0.46
    Activations Density 0.001%

    No Known Activations