© 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. 0-CLT-HP
    7. 42623
    Prev
    Next
    INDEX
    Explanations

    Open curly brace

    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
     nahilalakip
    -1.20
     betweenstory
    -1.08
    IsMutable
    -1.07
     propOrder
    -1.05
     متعلقه
    -1.02
     OFDb
    -0.95
    enumii
    -0.91
    awtextra
    -0.89
    ContentAsync
    -0.89
    yntaxException
    -0.88
    POSITIVE LOGITS
     stá
    0.49
     was
    0.48
     $
    0.47
     procedere
    0.46
    ...
    0.45
     trov
    0.45
    ,
    0.44
     dilakukan
    0.44
     CS
    0.43
     II
    0.42
    Activations Density 1.709%

    No Known Activations