© 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. 42942
    Prev
    Next
    INDEX
    Explanations

    control

    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
     églises
    -0.62
     control
    -0.61
     rayures
    -0.58
     Control
    -0.57
     commerciales
    -0.57
    ltä
    -0.56
     dieux
    -0.53
    "]);
    -0.52
    control
    -0.51
     écrits
    -0.50
    POSITIVE LOGITS
    BeginContext
    0.70
    ⓧ
    0.69
     referenties
    0.67
    ftagPool
    0.67
    
    0.67
     beginnetje
    0.66
     menstrual
    0.65
     erythro
    0.65
     biosynthesis
    0.64
     lactic
    0.64
    Activations Density 0.794%

    No Known Activations