© 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. 72222
    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
    MemoryWarning
    -0.68
    }$_
    -0.63
    PointerException
    -0.63
     defaultstate
    -0.62
    uxxxx
    -0.61
     estekak
    -0.59
     joindre
    -0.59
    Personendaten
    -0.58
    SourceChecksum
    -0.58
     Pilate
    -0.57
    POSITIVE LOGITS
    AddTagHelper
    0.52
    awtextra
    0.46
    enderror
    0.45
    kloped
    0.43
    ื่อน
    0.42
    scholar
    0.40
     evaluator
    0.39
     citer
    0.39
     science
    0.39
     attorney
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.