© 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. 0-CLT-HP
    7. 95157
    Prev
    Next
    INDEX
    Explanations

    acoustics

    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
     disambiguazione
    -1.05
    afficheront
    -1.02
     Signalez
    -1.01
    OGND
    -1.00
     Мексичка
    -0.99
    QMetaType
    -0.98
    تقاوى
    -0.95
     мәкал
    -0.95
     mauva
    -0.94
    ſelves
    -0.93
    POSITIVE LOGITS
     lot
    0.55
     control
    0.52
    ,
    0.47
     rare
    0.46
     corps
    0.46
     has
    0.45
     total
    0.44
     particular
    0.44
     
    0.44
     for
    0.44
    Activations Density 0.141%

    No Known Activations