© 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. 20-CLT-HP
    7. 73578
    Prev
    Next
    INDEX
    Explanations

    Computer code/technical language

    np_max-act-logits · 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
    oa̍t
    -0.87
     AssemblyCulture
    -0.80
     ostavi
    -0.77
     <<<<<<<<<<<<<<
    -0.71
    Билгалдахарш
    -0.70
    AnchorTagHelper
    -0.69
    MENAFN
    -0.68
    +#+
    -0.62
    __;
    -0.61
    mapStateToProps
    -0.61
    POSITIVE LOGITS
     awakeFromNib
    0.48
     runde
    0.40
    fib
    0.40
    OnPage
    0.40
    writeField
    0.40
    ɵɵ
    0.39
     Bär
    0.39
     msglen
    0.39
    fois
    0.38
    SceneManagement
    0.38
    Activations Density 0.001%

    No Known Activations