© 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. 4-CLT-HP
    7. 345
    Prev
    Next
    INDEX
    Explanations

    only just

    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
    __':
    -0.50
     tartalomajánló
    -0.50
     otomatig
    -0.49
    __':
    -0.46
     dalamnya
    -0.45
    Datuak
    -0.45
    gypti
    -0.43
     guste
    -0.43
     mesmos
    -0.43
     scorso
    -0.43
    POSITIVE LOGITS
     the
    1.02
     what
    0.80
     الاطلاع
    0.79
     their
    0.77
     a
    0.74
     its
    0.70
     in
    0.69
     because
    0.69
     during
    0.67
    readystatechange
    0.67
    Activations Density 0.001%

    No Known Activations