© 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. 1-CLT-HP
    7. 10465
    Prev
    Next
    INDEX
    Explanations

    ant

    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
    protoimpl
    -0.59
     fondation
    -0.55
    CppCodeGen
    -0.52
    StoreMessageInfo
    -0.51
    LiveData
    -0.50
    Trans
    -0.50
    dAtA
    -0.49
    eph
    -0.48
    клопе
    -0.47
     catég
    -0.47
    POSITIVE LOGITS
     "..\..\..\
    0.56
     "..\..\
    0.56
     SEDS
    0.54
    ngdoc
    0.53
     surla
    0.53
    aughey
    0.51
    GOTREF
    0.51
     ostavi
    0.50
     ***!
    0.49
     martens
    0.49
    Activations Density 0.065%

    No Known Activations