© 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. 98144
    Prev
    Next
    INDEX
    Explanations

    ordained

    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
     the
    -0.59
    balleur
    -0.57
    retanto
    -0.52
    ‌ی
    -0.49
    alnız
    -0.47
    owo
    -0.47
    Eksteraj
    -0.47
     their
    -0.46
     continuant
    -0.46
    <bos>
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.75
     nationalities
    0.70
    Tikang
    0.68
    reportWebVitals
    0.64
    +#+#
    0.64
     diagonals
    0.63
    VersionUID
    0.62
    awtextra
    0.60
     thereafter
    0.60
     initComponents
    0.59
    Activations Density 0.026%

    No Known Activations