© 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. 20-CLT-HP
    7. 76866
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · 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
     définiti
    -1.10
     auroit
    -1.06
     feroit
    -1.03
     supérieurs
    -1.01
     étoit
    -1.00
     ainfi
    -0.99
     colorés
    -0.99
     enfans
    -0.98
     normaux
    -0.96
     plufieurs
    -0.96
    POSITIVE LOGITS
    ><!--
    0.56
    ◄
    0.45
    SuppressLint
    0.45
     مشين
    0.44
    ScopeManager
    0.43
     administ
    0.42
     unveil
    0.42
    MethodManager
    0.42
     unveils
    0.41
     heavily
    0.41
    Activations Density 0.000%

    No Known Activations