© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5743
    Prev
    Next
    INDEX
    Explanations

    informal language (technical context)

    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
     have
    -0.52
     also
    -0.51
     تضيفلها
    -0.50
     come
    -0.49
     are
    -0.45
     at
    -0.44
     ones
    -0.43
     always
    -0.42
     đều
    -0.41
    ,
    -0.41
    POSITIVE LOGITS
    abestanden
    0.91
     Theſe
    0.86
     BrowserModule
    0.81
     Monfieur
    0.79
    WindowConstants
    0.78
    раздо
    0.76
     wikipagina
    0.76
     Beſ
    0.75
    Personendaten
    0.75
    Sucesor
    0.73
    Activations Density 0.013%

    No Known Activations