© 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. 5-CLT-HP
    7. 93676
    Prev
    Next
    INDEX
    Explanations

    units of time

    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
     Paglinawan
    -1.02
    تقاوى
    -0.89
    UserScript
    -0.88
     myſelf
    -0.85
     propOrder
    -0.83
    PropertyChanging
    -0.82
     Monfieur
    -0.82
    AutoScaleMode
    -0.81
     ✭✭
    -0.81
    contentLoaded
    -0.80
    POSITIVE LOGITS
     from
    0.52
    ward
    0.49
    —
    0.46
    2
    0.44
     far
    0.44
     ghép
    0.44
    .
    0.44
    far
    0.44
    removeChild
    0.44
     E
    0.44
    Activations Density 0.004%

    No Known Activations