© 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. 97356
    Prev
    Next
    INDEX
    Explanations

    global issues

    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
     OnInit
    -0.68
    contentLoaded
    -0.61
    GEBURTSDATUM
    -0.59
    cedido
    -0.58
    🏻‍♀️
    -0.57
    MockBean
    -0.57
     propOrder
    -0.56
    🏼
    -0.56
     simplifié
    -0.56
    서는
    -0.56
    POSITIVE LOGITS
     across
    0.50
     everywhere
    0.47
     SqlCommand
    0.47
     but
    0.47
    ,
    0.45
     today
    0.44
     wherever
    0.44
     artesanales
    0.43
     there
    0.42
     zdar
    0.42
    Activations Density 0.001%

    No Known Activations