© 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. 3145
    Prev
    Next
    INDEX
    Explanations

    finding the "best" option

    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
    ISupport
    -0.63
     تضيفلها
    -0.60
    setVerticalGroup
    -0.60
    FOOTNOTES
    -0.58
     Efq
    -0.56
    ViewFeatures
    -0.56
     Jefus
    -0.56
    ProgressHUD
    -0.55
     myſelf
    -0.54
    Offered
    -0.54
    POSITIVE LOGITS
    .
    0.57
     ujednoznacz
    0.49
    catraz
    0.49
     for
    0.48
     članak
    0.47
     MaterialApp
    0.45
    kmäler
    0.44
    !
    0.44
    verwijspagina
    0.43
    netbeans
    0.42
    Activations Density 0.003%

    No Known Activations