© 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. 4-CLT-HP
    7. 320
    Prev
    Next
    INDEX
    Explanations

    thoughts, feelings, beliefs

    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
     I
    -0.65
    PerformLayout
    -0.56
     we
    -0.54
    我們
    -0.54
    I
    -0.53
    harapkan
    -0.52
    我们
    -0.52
    We
    -0.51
     byste
    -0.50
     ours
    -0.50
    POSITIVE LOGITS
    contentLoaded
    0.75
     AssemblyProduct
    0.60
    TagMode
    0.59
    الحياه
    0.57
    évaluateur
    0.54
    Demografie
    0.54
    QMetaType
    0.54
    حياته
    0.54
     كمان
    0.52
     Roskov
    0.52
    Activations Density 0.001%

    No Known Activations