© 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. 0-CLT-HP
    7. 94992
    Prev
    Next
    INDEX
    Explanations

    CON

    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
     CON
    -0.96
    CON
    -0.91
    tory
    -0.44
     ко
    -0.41
    iya
    -0.41
    XO
    -0.40
    𝗢
    -0.40
     ο
    -0.40
    AddTagHelper
    -0.39
    truncated
    -0.39
    POSITIVE LOGITS
    expandindo
    0.95
    WebVitals
    0.78
    ьаж
    0.72
    elemField
    0.70
    GraphicsUnit
    0.69
     propOrder
    0.68
     мәкалә
    0.66
    Chham
    0.66
    ftagPool
    0.65
     Whittier
    0.64
    Activations Density 1.236%

    No Known Activations