© 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. 91737
    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
    -0.83
     createState
    -0.81
    GraphicsUnit
    -0.80
    "
    -0.79
     للمعارف
    -0.75
    ValueStyle
    -0.69
    makeConstraints
    -0.67
    “
    -0.66
    原始内容存档于
    -0.65
    "—
    -0.65
    POSITIVE LOGITS
    expandindo
    0.52
    ↵
    0.49
     Paglinawan
    0.44
     juridiques
    0.42
     peindre
    0.41
    .
    0.40
    .)
    0.40
     ).
    0.40
     виправивши
    0.39
     intercambio
    0.39
    Activations Density 0.000%

    No Known Activations