© 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. 4530
    Prev
    Next
    INDEX
    Explanations

    Start of documents

    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
    ThroughAttribute
    -0.57
    @[+][
    -0.57
    PointerException
    -0.54
     handleMessage
    -0.52
     censiti
    -0.50
    unmodifiable
    -0.50
    poni
    -0.50
    getline
    -0.50
     clearColor
    -0.49
     waw
    -0.49
    POSITIVE LOGITS
     técnicas
    0.52
     technologies
    0.51
     volontaire
    0.50
    NEGATIVE
    0.50
     critics
    0.49
     strategies
    0.49
    Spoljašnje
    0.49
     techniques
    0.49
    omsday
    0.48
    tempt
    0.48
    Activations Density 0.000%

    No Known Activations