© 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. 98196
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    szön
    -0.53
     Púb
    -0.53
    Entered
    -0.52
    ital
    -0.51
    WebVitals
    -0.50
    :✨
    -0.50
     läng
    -0.49
    Espèce
    -0.49
    入って
    -0.47
    msgSender
    -0.46
    POSITIVE LOGITS
    Hauptartikel
    0.59
    ocardio
    0.52
    فحة
    0.52
    cshtml
    0.52
    UnusedPrivate
    0.51
     MERCHANTABILITY
    0.50
     ellers
    0.50
    IonicModule
    0.48
     poveznice
    0.48
     continuant
    0.47
    Activations Density 0.002%

    No Known Activations