© 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. 4-CLT-HP
    7. 1852
    Prev
    Next
    INDEX
    Explanations

    -

    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
     kaarangay
    -0.61
    MessageOf
    -0.60
    !***
    -0.55
    lems
    -0.53
    icals
    -0.53
     sirens
    -0.52
    InitVars
    -0.50
    CopyWith
    -0.50
    UserScript
    -0.50
    opardy
    -0.50
    POSITIVE LOGITS
     AppCompat
    0.47
     Condu
    0.47
     hog
    0.46
    Trả
    0.46
     otomatig
    0.46
    matchCondition
    0.45
    ouv
    0.45
    angliski
    0.44
    twimg
    0.44
     quả
    0.43
    Activations Density 0.005%

    No Known Activations