© 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. 92003
    Prev
    Next
    INDEX
    Explanations

    for

    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
    IonicModule
    -0.57
    Politik
    -0.52
    queryInterface
    -0.51
     eccell
    -0.50
    átek
    -0.50
    kün
    -0.49
    ="">
    -0.48
    inama
    -0.48
    DataSetChanged
    -0.47
     NgModule
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.60
    AxisAlignment
    0.57
    ForRow
    0.54
    湃
    0.51
     ErrIntOverflow
    0.50
     Himself
    0.49
    isContained
    0.48
     Administrativna
    0.48
    DECREF
    0.47
     cellpadding
    0.47
    Activations Density 0.001%

    No Known Activations