© 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. 5139
    Prev
    Next
    INDEX
    Explanations

    these

    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
     nahilalakip
    -0.75
    HasAnnotation
    -0.54
    فحة
    -0.54
     linkovi
    -0.52
    RefNanny
    -0.51
    ;'>
    -0.50
    basePath
    -0.50
    /*++
    -0.50
    ✭✭
    -0.48
     digitais
    -0.48
    POSITIVE LOGITS
    ConstraintMaker
    0.72
    __(/*!
    0.71
    RectangleBorder
    0.65
     именно
    0.58
    AttributeSet
    0.57
    IBOutlet
    0.57
    AndEndTag
    0.55
    TestingModule
    0.55
    MigrationBuilder
    0.53
    WriteTagHelper
    0.51
    Activations Density 0.053%

    No Known Activations