© 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. 5499
    Prev
    Next
    INDEX
    Explanations

    least

    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
    numerusform
    -0.56
     समीक्षाएं
    -0.54
    żeli
    -0.53
     disambiguazione
    -0.51
     {?>
    -0.49
    multer
    -0.49
    diğim
    -0.49
    jspx
    -0.48
    opan
    -0.47
    уда
    -0.47
    POSITIVE LOGITS
     voorbij
    0.65
    énieur
    0.51
     giuri
    0.51
    kracht
    0.50
    subpackage
    0.49
     quæ
    0.49
     Penyakit
    0.49
    pions
    0.49
     omge
    0.49
     tombé
    0.48
    Activations Density 0.000%

    No Known Activations