© 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. 73520
    Prev
    Next
    INDEX
    Explanations

    Amy

    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
    AnchorTagHelper
    -0.57
     Вікі
    -0.46
    HasForeignKey
    -0.44
    Viki
    -0.43
     veckor
    -0.43
    łaś
    -0.43
    ResumeLayout
    -0.42
    tulo
    -0.41
     afk
    -0.41
     tribune
    -0.41
    POSITIVE LOGITS
     تضيفلها
    0.83
    ⓧ
    0.64
    AccessorTable
    0.61
    GOTREF
    0.60
     ISTAT
    0.54
     Administrativna
    0.54
    orteur
    0.54
    ɵɵelementStart
    0.52
    XmlEnum
    0.52
    ścić
    0.50
    Activations Density 0.005%

    No Known Activations