© 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. 4853
    Prev
    Next
    INDEX
    Explanations

    a

    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
    AddTagHelper
    -1.16
    ValueStyle
    -1.00
    WaitGroup
    -0.97
    ConstraintMaker
    -0.94
    enderror
    -0.94
    SequentialGroup
    -0.93
    ScopeManager
    -0.91
    <bos>
    -0.90
     Мексичка
    -0.89
    StructEnd
    -0.88
    POSITIVE LOGITS
     or
    0.59
     U
    0.54
     fan
    0.54
    ,
    0.53
     online
    0.51
     parent
    0.48
     business
    0.48
     senior
    0.46
     local
    0.45
     businesses
    0.45
    Activations Density 0.001%

    No Known Activations