© 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. 1-CLT-HP
    7. 9724
    Prev
    Next
    INDEX
    Explanations

    display

    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
    
    -0.63
     tục
    -0.53
    ellido
    -0.51
     geslacht
    -0.50
     perpé
    -0.49
    WebVitals
    -0.48
    engarkan
    -0.48
     elettron
    -0.48
    AsUp
    -0.48
     ganglion
    -0.48
    POSITIVE LOGITS
    fjspx
    0.62
    AutoField
    0.52
    oub
    0.46
    '){
    0.45
    nope
    0.45
    殊
    0.44
    stdc
    0.44
    anique
    0.44
    Lip
    0.44
    Diff
    0.44
    Activations Density 0.075%

    No Known Activations