© 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. 76461
    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
    ÑOS
    -0.57
    oplasma
    -0.53
     $__
    -0.48
    isholm
    -0.48
    hiza
    -0.47
     Irm
    -0.47
     Dör
    -0.47
    ız
    -0.46
     couver
    -0.45
    vum
    -0.45
    POSITIVE LOGITS
     propOrder
    0.73
     AssemblyCompany
    0.68
     صوتيه
    0.64
     nakalista
    0.59
    NameInMap
    0.55
     ujednoznacz
    0.53
     समीक्षाओं
    0.52
     незавершена
    0.52
    ":[{
    0.50
    oa̍t
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.