© 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. 98229
    Prev
    Next
    INDEX
    Explanations

    discussion

    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
    setContentView
    -0.52
    prepareStatement
    -0.52
     toolStrip
    -0.50
    stdafx
    -0.49
    WebServlet
    -0.49
     onCreateView
    -0.48
    IVAS
    -0.48
    forRoot
    -0.47
    日閲覧
    -0.47
    DllImport
    -0.47
    POSITIVE LOGITS
     estekak
    0.69
    RegistryLite
    0.65
    TypedDataSet
    0.64
    ьаж
    0.61
    WriteBarrier
    0.60
    ReusableCell
    0.57
    SharedDtor
    0.52
    thâu
    0.51
    InitVars
    0.49
     Италијани
    0.48
    Activations Density 0.003%

    No Known Activations