© 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. 94377
    Prev
    Next
    INDEX
    Explanations

    .

    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
    Lähteet
    -0.76
     hObject
    -0.69
    WithIOException
    -0.67
    UnusedPrivate
    -0.66
    nonatomic
    -0.64
    FontOfSize
    -0.63
     AssemblyTitle
    -0.63
    exactly
    -0.61
    出版年
    -0.61
    ArrowToggle
    -0.60
    POSITIVE LOGITS
    verwijspagina
    0.71
    alls
    0.51
    Personensuche
    0.48
    Dienst
    0.48
     Apre
    0.47
    apeake
    0.46
    spyOn
    0.45
    dahl
    0.45
    glicher
    0.45
     díl
    0.44
    Activations Density 0.003%

    No Known Activations