© 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. 95193
    Prev
    Next
    INDEX
    Explanations

    tests/assessments

    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
    ("")]
    -0.56
     his
    -0.50
    ogie
    -0.49
    ("")]
    -0.48
     processus
    -0.47
     sûr
    -0.47
     die
    -0.46
     nov
    -0.46
    uwen
    -0.46
     four
    -0.45
    POSITIVE LOGITS
     initComponents
    0.75
     NSCoder
    0.71
     betweenstory
    0.71
     myſelf
    0.71
    PerformLayout
    0.70
    ArrowToggle
    0.70
     sherds
    0.68
    roxene
    0.68
     pliers
    0.66
     photolibrary
    0.65
    Activations Density 0.207%

    No Known Activations