© 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. 72391
    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
    ]")]
    -0.50
    อง
    -0.40
    ically
    -0.40
     dates
    -0.40
    MemoryWarning
    -0.40
    keyValue
    -0.39
     dated
    -0.39
     slå
    -0.39
    VOLUME
    -0.38
     بتاريخ
    -0.38
    POSITIVE LOGITS
    PreferredItem
    0.97
    tagHelperRunner
    0.94
     protoimpl
    0.88
     TextAppearance
    0.83
     '\\;'
    0.77
    évaluateur
    0.67
    IndentedString
    0.65
    AndroidJUnit
    0.63
     jadx
    0.62
    WithIOException
    0.62
    Activations Density 0.002%

    No Known Activations