© 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. 4620
    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
    ry
    -0.54
    sedes
    -0.52
    y
    -0.51
    gy
    -0.48
    aus
    -0.47
    matic
    -0.46
    ISTIC
    -0.45
    vá
    -0.44
    eterminate
    -0.44
    erson
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    1.08
    SequentialGroup
    0.87
    principalTable
    0.80
     AssemblyCulture
    0.78
    styleType
    0.75
    WebVitals
    0.72
     EconPapers
    0.69
    PreExecute
    0.69
    DoubleQuotes
    0.66
    VersionUID
    0.65
    Activations Density 0.004%

    No Known Activations