© 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. 71738
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · 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
    StructEnd
    -0.66
    OGND
    -0.55
    
    -0.55
    CloseOperation
    -0.55
    MessageTagHelper
    -0.54
     تعدى
    -0.53
     bezeichneter
    -0.52
    Legături
    -0.52
    FunctionFlags
    -0.51
    WriteAttribute
    -0.50
    POSITIVE LOGITS
     pit
    0.66
     nonatomic
    0.60
    ttä
    0.57
     beating
    0.56
    SequentialGroup
    0.54
    Pit
    0.54
    beaten
    0.54
    ConstraintMaker
    0.52
     pits
    0.52
    Facades
    0.52
    Activations Density 0.000%

    No Known Activations