© 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. 5-CLT-HP
    7. 97989
    Prev
    Next
    INDEX
    Explanations

    0

    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
    -0.50
    ystis
    -0.49
    setTypeface
    -0.49
    acta
    -0.47
    oplas
    -0.45
    câ
    -0.44
    tat
    -0.44
    нан
    -0.44
    row
    -0.43
    mc
    -0.42
    POSITIVE LOGITS
    rungsseite
    0.83
    SequentialGroup
    0.77
     Paglinawan
    0.77
    ServletException
    0.75
    TestingModule
    0.71
    yntaxException
    0.69
    URLException
    0.68
     Monfieur
    0.66
     Bourgoin
    0.65
     typelib
    0.64
    Activations Density 0.001%

    No Known Activations