© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72687
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    writeFieldEnd
    -0.70
    enumi
    -0.65
    EndProject
    -0.63
    ctically
    -0.62
    ApplicationTests
    -0.62
     AssemblyTitle
    -0.61
     snippetHide
    -0.60
     fieldNum
    -0.58
    bonucle
    -0.55
    Билгалдахарш
    -0.53
    POSITIVE LOGITS
     FREEDOM
    0.47
     freedoms
    0.47
     خارجية
    0.43
    *~*~
    0.43
     freedom
    0.42
     Harbor
    0.42
     idio
    0.42
     gagne
    0.42
    คล
    0.41
     avanzado
    0.41
    Activations Density 0.000%

    No Known Activations