© 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. 76323
    Prev
    Next
    INDEX
    Explanations

    Education, code, and copyright

    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
    bootstrapcdn
    -0.79
     ProtoMessage
    -0.70
    ьаж
    -0.63
     scolas
    -0.63
    }>;
    -0.61
     okul
    -0.59
     initComponents
    -0.59
     university
    -0.59
     betweenstory
    -0.58
    исленность
    -0.58
    POSITIVE LOGITS
    [++
    0.55
     element
    0.53
     BeautifulSoup
    0.51
    element
    0.50
     Element
    0.50
    ISupport
    0.50
     $"{
    0.49
     post
    0.48
     member
    0.47
     pilota
    0.47
    Activations Density 0.000%

    No Known Activations