© 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. 9545
    Prev
    Next
    INDEX
    Explanations

    emergency

    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
     blessés
    -0.75
     nonUne
    -0.71
    fromnode
    -0.63
     '\\;'
    -0.60
     calendriers
    -0.60
     médicaux
    -0.59
     MessageBoxIcon
    -0.58
    nictwa
    -0.58
     stratégique
    -0.57
     judiciaire
    -0.56
    POSITIVE LOGITS
    WebMethod
    0.59
     Tre
    0.56
    πάρχ
    0.55
    发表于
    0.54
    ViewFeatures
    0.54
    ppia
    0.52
    Gemeinsame
    0.52
    Tre
    0.52
    ftagPool
    0.52
     nahilalakip
    0.51
    Activations Density 0.011%

    No Known Activations