© 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. 142
    Prev
    Next
    INDEX
    Explanations

    time

    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
    כשיו
    -0.40
    Finally
    -0.40
    Now
    -0.38
    JRadioButton
    -0.38
     iprot
    -0.38
     zich
    -0.38
     hız
    -0.38
     Finally
    -0.36
     sich
    -0.36
    ρκ
    -0.36
    POSITIVE LOGITS
    Personendaten
    0.98
     autorytatywna
    0.91
    findpost
    0.90
    Билгалдахарш
    0.82
    Portale
    0.80
    Enllaces
    0.74
    UserScript
    0.73
     مشين
    0.73
     kaarangay
    0.72
     незавершена
    0.71
    Activations Density 0.003%

    No Known Activations