© 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. 4-CLT-HP
    7. 1407
    Prev
    Next
    INDEX
    Explanations

    the

    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
    matic
    -0.49
     فريبيس
    -0.48
    matically
    -0.45
    anyahu
    -0.45
     MIC
    -0.45
     conto
    -0.45
    aters
    -0.44
     technique
    -0.43
     adjustment
    -0.43
     microphone
    -0.42
    POSITIVE LOGITS
    CppCodeGen
    0.57
     mauvaises
    0.56
     Walkover
    0.54
     gouttes
    0.54
     D
    0.54
    Zitat
    0.54
     For
    0.54
    beginPath
    0.53
     autorytatywna
    0.52
     finestra
    0.52
    Activations Density 0.002%

    No Known Activations