© 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. 1-CLT-HP
    7. 9088
    Prev
    Next
    INDEX
    Explanations

    tutorials and technical information

    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
    lot
    -0.59
    auce
    -0.59
     kasarigan
    -0.55
     Demonstrate
    -0.52
    údo
    -0.52
    INTO
    -0.51
     الرياضيه
    -0.51
    )|^{
    -0.51
     bezeichneter
    -0.50
    STRO
    -0.48
    POSITIVE LOGITS
    findpost
    0.69
    fillType
    0.65
    iprot
    0.63
    ImageContext
    0.59
    zeera
    0.55
     imageNamed
    0.51
    createServer
    0.51
    Palmarès
    0.50
     Phari
    0.50
     Aene
    0.50
    Activations Density 0.028%

    No Known Activations