© 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. 1-CLT-HP
    7. 10420
    Prev
    Next
    INDEX
    Explanations

    directions

    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
     <<<<<<<<<<<<<<
    -0.64
    oredCriteria
    -0.55
     cherchés
    -0.54
    voo
    -0.50
    tilo
    -0.49
    Sc
    -0.49
     menyes
    -0.48
    
    -0.46
    papers
    -0.46
     onts
    -0.46
    POSITIVE LOGITS
     Audiodateien
    0.66
    setVerticalGroup
    0.59
     betweenstory
    0.56
     BorderRadius
    0.54
     برانيه
    0.54
     trinh
    0.54
     Réalisation
    0.53
    Hauptartikel
    0.53
    UVWXYZ
    0.52
     مشارکت‌کنندگان
    0.51
    Activations Density 0.014%

    No Known Activations