© 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. 5-CLT-HP
    7. 3122
    Prev
    Next
    INDEX
    Explanations

    Code/documentation snippets

    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
     of
    -0.48
    บค
    -0.41
     norsk
    -0.40
     mar
    -0.38
     nobile
    -0.38
     nacional
    -0.37
    ensement
    -0.37
     to
    -0.37
     pell
    -0.36
    neté
    -0.36
    POSITIVE LOGITS
    OGND
    1.02
    oa̍t
    0.84
     виправивши
    0.81
    SharedDtor
    0.76
    LabelTagHelper
    0.76
     tartalomajánló
    0.73
     незавершена
    0.73
     kasarigan
    0.71
    DockStyle
    0.70
    PerformLayout
    0.68
    Activations Density 0.002%

    No Known Activations