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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2428
    Prev
    Next
    INDEX
    Explanations

    power

    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
    viewDidLoad
    -0.62
    addCriterion
    -0.62
    isert
    -0.55
    Portail
    -0.54
    PullParser
    -0.53
     wikipagina
    -0.51
    Ведь
    -0.50
    ised
    -0.50
    IUrlHelper
    -0.50
    ]--;
    -0.48
    POSITIVE LOGITS
    SequentialGroup
    0.70
    ViewFeatures
    0.68
    ChildScrollView
    0.56
    abank
    0.53
     Normdatei
    0.52
    zeera
    0.49
    Personendaten
    0.48
     utafitiHapana
    0.47
    первых
    0.46
    RunAsync
    0.46
    Activations Density 0.000%

    No Known Activations