© 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. 1-CLT-HP
    7. 14255
    Prev
    Next
    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash
    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
    ","","
    -0.67
     thereto
    -0.63
     ModelExpression
    -0.62
     times
    -0.58
     therein
    -0.54
     Jérusalem
    -0.53
    Anytime
    -0.52
     behavior
    -0.52
    synchronized
    -0.51
    behavior
    -0.50
    POSITIVE LOGITS
    SharedDtor
    0.65
     thousands
    0.61
     /\.
    0.59
     <>",
    0.59
    AsUp
    0.58
    thousands
    0.56
    انيف
    0.56
    bootstrapcdn
    0.54
     ISNI
    0.53
     propOrder
    0.53
    Activations Density 0.012%

    No Known Activations