© 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. 97647
    Prev
    Next
    INDEX
    Explanations

    s

    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
    GEBURTS
    -0.48
     leads
    -0.48
     Référence
    -0.46
     proper
    -0.46
     فريبيس
    -0.45
    املة
    -0.45
     Leads
    -0.45
    __["
    -0.45
    Personendaten
    -0.44
     tartalomajánló
    -0.43
    POSITIVE LOGITS
     iprot
    0.68
     HttpServlet
    0.63
     postIndex
    0.61
     StringTokenizer
    0.57
     incomplète
    0.55
    раздо
    0.54
    CodedInputStream
    0.54
    看你
    0.53
    InitVars
    0.53
    AddTagHelper
    0.53
    Activations Density 0.001%

    No Known Activations