© 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. 0-CLT-HP
    7. 42504
    Prev
    Next
    INDEX
    Explanations

    GET

    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
     GET
    -0.68
     Get
    -0.52
     XCTest
    -0.49
     doGet
    -0.47
    kloped
    -0.46
    oug
    -0.45
    })));
    -0.44
    uvres
    -0.43
    GET
    -0.42
     мәкалә
    -0.41
    POSITIVE LOGITS
    ReusableCell
    0.88
    InputBorder
    0.84
    WriteBarrier
    0.78
    parsedMessage
    0.73
     becauſe
    0.70
     itſelf
    0.68
    OGND
    0.67
     chanter
    0.65
     BoxDecoration
    0.64
     referenties
    0.63
    Activations Density 1.562%

    No Known Activations