© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93611
    Prev
    Next
    INDEX
    Explanations

    etine

    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
    
    -0.85
     pour
    -0.75
     Audiodateien
    -0.69
    Примітки
    -0.64
    __":
    -0.63
    expandindo
    -0.61
    etine
    -0.61
     незавершена
    -0.58
    сылкі
    -0.57
     الحره
    -0.57
    POSITIVE LOGITS
     additions
    0.58
     Hinds
    0.55
     addition
    0.55
    glBegin
    0.53
     the
    0.52
     survivors
    0.52
     arrivals
    0.52
    stuk
    0.52
    canth
    0.52
     Heaton
    0.52
    Activations Density 0.122%

    No Known Activations