© 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. 5-CLT-HP
    7. 93734
    Prev
    Next
    INDEX
    Explanations

    learns

    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
     learn
    -1.06
     learns
    -1.05
     Learn
    -0.99
     متعلقه
    -0.99
    learn
    -0.95
     Learning
    -0.94
    apprendre
    -0.91
     aprende
    -0.91
     learned
    -0.90
    Learning
    -0.90
    POSITIVE LOGITS
    Itoa
    0.43
    (()
    0.43
     Ngb
    0.42
    метри
    0.42
    argmax
    0.42
     disbelief
    0.41
     absence
    0.40
     moment
    0.40
    lighed
    0.39
     XMLHttpRequest
    0.39
    Activations Density 0.000%

    No Known Activations