© 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. 20-CLT-HP
    7. 77366
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    PreferredItem
    -0.83
     AssemblyCulture
    -0.81
    HasForeignKey
    -0.77
    Билгалдахарш
    -0.77
     Roskov
    -0.75
    StoryboardSegue
    -0.75
     NSCoder
    -0.72
    prefixer
    -0.72
    CloseOperation
    -0.70
     EconPapers
    -0.70
    POSITIVE LOGITS
     shoots
    0.55
     powers
    0.54
     hits
    0.49
     forms
    0.49
     touches
    0.47
     sends
    0.45
     wipes
    0.45
     causes
    0.44
    ftes
    0.44
    seteq
    0.43
    Activations Density 0.001%

    No Known Activations