© 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. 5-CLT-HP
    7. 91886
    Prev
    Next
    INDEX
    Explanations

    world

    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
    ValueGeneration
    -0.58
     عنه
    -0.57
     عنها
    -0.56
     dieux
    -0.55
    TagMode
    -0.53
     bort
    -0.53
    qu
    -0.52
    kloped
    -0.52
    Kaynakça
    -0.50
    Хьажоргаш
    -0.50
    POSITIVE LOGITS
    initComponents
    0.57
     where
    0.55
     with
    0.55
    adari
    0.54
    raborty
    0.50
    segments
    0.49
    APORE
    0.49
    hyrchwyd
    0.49
    haël
    0.49
     cysts
    0.48
    Activations Density 0.000%

    No Known Activations