© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3195
    Prev
    Next
    INDEX
    Explanations

    dates

    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
     surla
    -0.61
     تانيه
    -0.54
    +#+#
    -0.54
     '\\;'
    -0.53
    <bos>
    -0.53
    Personensuche
    -0.52
    AddTagHelper
    -0.48
    wieś
    -0.47
    OGND
    -0.47
    EDEFAULT
    -0.47
    POSITIVE LOGITS
    naeus
    0.61
    Lähteet
    0.59
    Pageable
    0.59
    روابط
    0.57
    veien
    0.56
     Unidas
    0.56
    lehem
    0.54
    orias
    0.54
     AssemblyTitle
    0.54
     vectors
    0.53
    Activations Density 0.009%

    No Known Activations