© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90880
    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
    Negative Logits
    tvguidetime
    -0.88
     jsPsych
    -0.67
    TargetException
    -0.67
    adaptiveStyles
    -0.65
    apunov
    -0.65
     ||
    -0.64
    //
    -0.63
    ValueGenerated
    -0.62
     ujednoznacz
    -0.62
    esModule
    -0.60
    POSITIVE LOGITS
     صوتيه
    0.51
     bo
    0.49
     Boo
    0.46
    mba
    0.45
    bo
    0.45
     ویکی‌پدی
    0.45
    CodedInputStream
    0.45
    GEBURTSDATUM
    0.45
    Msp
    0.43
    AddHtmlAttribute
    0.43
    Activations Density 0.001%

    No Known Activations