© 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. 72185
    Prev
    Next
    INDEX
    Explanations

    Technical/academic writing

    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
    VersionUID
    -0.61
    
    -0.57
     <<<<<<<<<<<<<<
    -0.57
     ['$
    -0.52
    ⓧ
    -0.51
    jgl
    -0.50
    ioutil
    -0.47
     skippy
    -0.46
     unittest
    -0.46
    poque
    -0.46
    POSITIVE LOGITS
    StoryboardSegue
    0.80
     EconPapers
    0.70
     long
    0.69
    RTEX
    0.60
    блок
    0.57
    TagMode
    0.57
    SerializedSize
    0.56
    tonsoft
    0.56
    FunctionFlags
    0.55
    zeiger
    0.54
    Activations Density 0.001%

    No Known Activations