© 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. 98204
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
    +#+
    -0.69
     InputDecoration
    -0.69
    ArgumentParser
    -0.62
    Tikang
    -0.60
    +#+#
    -0.60
    reportWebVitals
    -0.59
    ]--;
    -0.58
    createStatement
    -0.58
    SBATCH
    -0.58
    sedown
    -0.57
    POSITIVE LOGITS
     then
    0.75
    then
    0.59
     to
    0.55
     Then
    0.53
     THEN
    0.52
    Kemudian
    0.51
     that
    0.49
    Then
    0.49
    szönöm
    0.49
     entonces
    0.49
    Activations Density 0.001%

    No Known Activations