© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92530
    Prev
    Next
    INDEX
    Explanations

    Topics

    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
    Topics
    -0.83
     topics
    -0.65
    AxisAlignment
    -0.63
     հղումներ
    -0.63
    كويكب
    -0.63
    
    -0.61
    enumii
    -0.61
    HomeAsUpEnabled
    -0.60
     sewerage
    -0.57
     intptr
    -0.56
    POSITIVE LOGITS
    %)$
    0.48
    tein
    0.48
    ंदीखरीदारी
    0.47
     vers
    0.45
    ElementException
    0.45
    urte
    0.44
     elimination
    0.44
     karşı
    0.42
     earth
    0.42
     Vikipedi
    0.41
    Activations Density 0.208%

    No Known Activations