© 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. 5-CLT-HP
    7. 97076
    Prev
    Next
    INDEX
    Explanations

    technical problems/solutions

    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
    EDEFAULT
    -0.54
    cea
    -0.53
     phép
    -0.52
     ExecuteAsync
    -0.50
     Процитовано
    -0.49
    Datagram
    -0.49
     impossível
    -0.48
    忌
    -0.47
    ROGEN
    -0.46
     offence
    -0.46
    POSITIVE LOGITS
    ReusableCell
    0.75
     AssemblyProduct
    0.62
    astéroïdes
    0.57
    ]")]
    0.57
     سكانية
    0.56
    ברס
    0.54
    oredCriteria
    0.53
     ostavi
    0.52
     Paglinawan
    0.52
     Numerade
    0.51
    Activations Density 0.001%

    No Known Activations