© 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. 0-CLT-HP
    7. 93229
    Prev
    Next
    INDEX
    Explanations

    quen

    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
     quench
    -0.57
    quen
    -0.54
    dstuk
    -0.52
    ias
    -0.51
     exemplaire
    -0.47
     marred
    -0.47
    tests
    -0.47
     ear
    -0.47
    ared
    -0.47
    Apa
    -0.47
    POSITIVE LOGITS
     HttpNotFound
    0.70
    endphp
    0.69
     الرياضيه
    0.67
    GEBURTSDATUM
    0.64
     disambiguazione
    0.63
     betweenstory
    0.63
    Lähteet
    0.61
    BeginContext
    0.60
    Alike
    0.60
     FormBuilder
    0.60
    Activations Density 0.145%

    No Known Activations