© 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. 0-CLT-HP
    7. 43059
    Prev
    Next
    INDEX
    Explanations

    made

    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
     made
    -1.14
    made
    -0.94
    Made
    -0.86
     Made
    -0.76
    <bos>
    -0.75
    '
    -0.75
     make
    -0.63
    ’
    -0.63
    make
    -0.60
     makes
    -0.58
    POSITIVE LOGITS
    tagHelperRunner
    1.15
     EconPapers
    1.15
    Personendaten
    1.15
     AssemblyProduct
    1.02
     '\\;'
    1.02
     MainAxisSize
    1.01
    IntoConstraints
    0.99
     Мексичка
    0.98
     تضيفلها
    0.98
    Hozzáférés
    0.98
    Activations Density 0.035%

    No Known Activations