© 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. 75709
    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
    -1.28
    ,
    -1.26
    InputBorder
    -1.19
     ProtoMessage
    -1.14
    Datuak
    -1.11
    NewUrlParser
    -1.09
    \{\\
    -1.09
     snippetHide
    -1.07
    NameInMap
    -1.06
     AssemblyCulture
    -1.05
    POSITIVE LOGITS
    (&
    0.24
     lainnya
    0.23
     sebagai
    0.23
     attraverso
    0.21
     setelah
    0.21
     melalui
    0.20
    ();
    0.19
     appelée
    0.19
     sebelum
    0.17
     valamint
    0.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.