© 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. 10954
    Prev
    Next
    INDEX
    Explanations

    chronic

    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
    Tikang
    -0.85
    enegal
    -0.73
    UserScript
    -0.71
    enchymal
    -0.70
     wireType
    -0.67
    imothy
    -0.67
    iastes
    -0.65
     []:
    -0.65
    ImageContext
    -0.64
    ieteur
    -0.64
    POSITIVE LOGITS
     ExecuteAsync
    0.57
     ddelweddau
    0.54
     OnInit
    0.46
    tagext
    0.38
     dafür
    0.38
    //
    0.37
    /*
    0.36
     Dir
    0.36
     living
    0.36
     z
    0.36
    Activations Density 0.048%

    No Known Activations