© 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. 91754
    Prev
    Next
    INDEX
    Explanations

    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
    dataGridView
    -0.48
    ilea
    -0.46
     struggle
    -0.43
    __);
    -0.42
    sodik
    -0.42
    nake
    -0.41
    gyi
    -0.41
    ذة
    -0.40
    deniz
    -0.40
     quantitative
    -0.40
    POSITIVE LOGITS
     nahilalakip
    0.90
    SequentialGroup
    0.72
     configureStore
    0.68
    +#+
    0.67
    WireFormatLite
    0.66
     تضيفلها
    0.65
    getActiveSheet
    0.65
    SharedCtor
    0.64
    PageModule
    0.61
    ніципа
    0.61
    Activations Density 0.005%

    No Known Activations