© 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. 72584
    Prev
    Next
    INDEX
    Explanations

    out/in

    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
    SharedCtor
    -0.63
     initComponents
    -0.49
    styleable
    -0.46
     cubana
    -0.45
     NSCoder
    -0.45
     Andrei
    -0.44
     Rena
    -0.44
    eeeeeeee
    -0.43
     архивлан
    -0.43
    forChild
    -0.43
    POSITIVE LOGITS
    put
    1.16
     put
    1.09
    take
    1.02
    Put
    1.00
    puts
    0.98
    coming
    0.94
     puts
    0.92
    takes
    0.91
    putting
    0.91
    comes
    0.85
    Activations Density 0.079%

    No Known Activations