© 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. 4-CLT-HP
    7. 2014
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    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
    Lähteet
    -0.52
    //
    -0.48
    Transkript
    -0.47
    fseek
    -0.47
     <<<<<<<<<<<<<<
    -0.47
    writerow
    -0.47
    RTEX
    -0.47
    სქოლიო
    -0.46
     numai
    -0.45
    ToAction
    -0.45
    POSITIVE LOGITS
     كومونز
    0.70
    fjspx
    0.63
    Vidite
    0.57
     disambiguazione
    0.56
    losseum
    0.53
     building
    0.52
     Building
    0.51
    '])){
    0.50
    imir
    0.50
     میلیارد
    0.50
    Activations Density 0.000%

    No Known Activations