© 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. 1-CLT-HP
    7. 13984
    Prev
    Next
    INDEX
    Explanations

    code

    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
     inac
    -0.47
     Sequo
    -0.42
    Herzlich
    -0.40
    siąż
    -0.38
    thè
    -0.37
    Globals
    -0.37
     hoy
    -0.37
    zysz
    -0.37
    past
    -0.36
    ellige
    -0.36
    POSITIVE LOGITS
    TestingModule
    0.91
     дописавши
    0.85
    Autoritní
    0.84
    NameInMap
    0.77
    PerformLayout
    0.75
    EndInit
    0.74
    SharedDtor
    0.74
    CodeAttribute
    0.74
     ModelExpression
    0.73
     चीज़ों
    0.71
    Activations Density 0.087%

    No Known Activations