© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95117
    Prev
    Next
    INDEX
    Explanations

    legitimacy

    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
    usercontent
    -0.69
     IndexPath
    -0.68
    UnsafeEnabled
    -0.66
    Personendaten
    -0.65
    Autoritní
    -0.64
    pædia
    -0.60
    conta
    -0.59
    IUrlHelper
    -0.58
    webElementXpaths
    -0.58
    theless
    -0.56
    POSITIVE LOGITS
     nascita
    0.48
     bruk
    0.46
    ✭✭
    0.45
     Utilisez
    0.44
     Ruler
    0.44
     debout
    0.43
    зной
    0.43
     bordes
    0.43
     laterales
    0.42
    i
    0.42
    Activations Density 0.000%

    No Known Activations