© 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. 5-CLT-HP
    7. 98203
    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
    Jereo
    -0.52
     للاسماء
    -0.51
    SPJ
    -0.50
     JpaRepository
    -0.50
    BorderFactory
    -0.49
    ItemBackground
    -0.47
    fich
    -0.47
    )"),
    -0.45
    ället
    -0.45
    opro
    -0.45
    POSITIVE LOGITS
    windowFixed
    0.78
     متعلقه
    0.61
     nakalista
    0.60
    RTLR
    0.58
    UnsafeEnabled
    0.57
    Committed
    0.56
     Мексичка
    0.54
    EndContext
    0.53
    UnknownFieldSet
    0.53
    houettes
    0.49
    Activations Density 0.001%

    No Known Activations