© 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. 20-CLT-HP
    7. 73783
    Prev
    Next
    INDEX
    Explanations

    to

    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
     препратки
    -0.69
     MenuView
    -0.65
     تضيفلها
    -0.64
    BASEPATH
    -0.61
     cherchés
    -0.61
    Nationalité
    -0.60
    styleType
    -0.60
     together
    -0.60
    ⓘ
    -0.59
    MethodType
    -0.59
    POSITIVE LOGITS
     pool
    1.08
     band
    1.01
     work
    1.00
     Pool
    0.85
    pool
    0.80
     pools
    0.79
     POOL
    0.75
    Pool
    0.71
    work
    0.70
    band
    0.68
    Activations Density 0.002%

    No Known Activations