© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 72030
    Prev
    Next
    INDEX
    Explanations

    Code and special characters

    np_max-act-logits · 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
     Sotto
    -0.40
    SceneManager
    -0.40
    verwijspagina
    -0.39
     accidente
    -0.39
    hoge
    -0.38
     NUnit
    -0.37
     Veja
    -0.37
     distress
    -0.36
     Setter
    -0.36
     cones
    -0.35
    POSITIVE LOGITS
    BeginContext
    0.88
    WebVitals
    0.82
    ftagPool
    0.73
     kaarangay
    0.72
     فريبيس
    0.70
     esternos
    0.69
     ویکی‌پدی
    0.69
    Abitanti
    0.67
    IntoConstraints
    0.67
    Controllo
    0.66
    Activations Density 0.001%

    No Known Activations