© 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. 5-CLT-HP
    7. 3625
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    UNCIL
    -0.47
    כש
    -0.47
    msgTypes
    -0.47
     green
    -0.47
    casio
    -0.46
     who
    -0.44
    green
    -0.44
    록
    -0.44
    scal
    -0.44
     program
    -0.43
    POSITIVE LOGITS
    WriteAttribute
    0.79
    IntoConstraints
    0.78
    WebVitals
    0.69
    TagHelper
    0.69
    astéroïdes
    0.68
    //});
    0.68
    sizeCache
    0.65
     SafeMath
    0.65
    principalColumn
    0.65
    Abitanti
    0.64
    Activations Density 0.003%

    No Known Activations