© 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. 5065
    Prev
    Next
    INDEX
    Explanations

    on

    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
     financières
    -0.66
     présidenti
    -0.63
     noires
    -0.62
    ✭✭
    -0.60
     proposées
    -0.57
     supérieures
    -0.57
     ordinaires
    -0.55
     vertes
    -0.54
     culturelles
    -0.54
     étrangères
    -0.54
    POSITIVE LOGITS
    Diweddarwch
    0.65
    TEMPO
    0.60
    mitive
    0.57
    ]--;
    0.57
    polation
    0.56
     criticism
    0.54
     keyPressed
    0.54
    ubri
    0.52
     critics
    0.52
    DeleteBehavior
    0.52
    Activations Density 0.003%

    No Known Activations