© 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. 5-CLT-HP
    7. 4007
    Prev
    Next
    INDEX
    Explanations

    notice

    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
    .
    -0.63
    routeProvider
    -0.60
     doInBackground
    -0.58
     <<<<<<<<<<<<<<
    -0.55
    SharedDtor
    -0.54
     as
    -0.52
    ArgumentParser
    -0.52
    dasarkan
    -0.52
     in
    -0.51
    PreAuthorize
    -0.51
    POSITIVE LOGITS
    WebElementEntity
    0.71
    OGND
    0.59
    NameInMap
    0.58
    
    0.56
    findpost
    0.56
    GOTREF
    0.52
     sale
    0.51
    oflu
    0.51
     الرياضيه
    0.51
    ulare
    0.49
    Activations Density 0.008%

    No Known Activations