© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14141
    Prev
    Next
    INDEX
    Explanations

    ges

    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
     watercolor
    -0.85
     watercolour
    -0.75
     Watercolor
    -0.65
    watercolor
    -0.64
    <caption>
    -0.52
    acos
    -0.51
    //</
    -0.50
    pidou
    -0.49
     scienza
    -0.48
    adpleegd
    -0.48
    POSITIVE LOGITS
    ist
    0.81
    ing
    0.80
    ism
    0.69
     للمعارف
    0.67
    ists
    0.65
    ally
    0.64
    ial
    0.56
    ation
    0.56
    ed
    0.56
    شهاد
    0.55
    Activations Density 0.016%

    No Known Activations