© 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. 91580
    Prev
    Next
    INDEX
    Explanations

    thermoplastic

    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
    mener
    -0.50
     Proctor
    -0.50
     HasFactory
    -0.49
     continúas
    -0.49
    pecting
    -0.48
    TOC
    -0.47
    Fuente
    -0.47
    setToolTipText
    -0.47
    UBL
    -0.46
     \@
    -0.46
    POSITIVE LOGITS
    ity
    0.64
    Искәрмәләр
    0.62
    SharedCtor
    0.59
     Infórmanos
    0.57
    الحياه
    0.55
    verwijspagina
    0.55
    Diweddarwch
    0.52
     ujednoznacz
    0.50
    Jeografia
    0.49
    PerformLayout
    0.49
    Activations Density 0.001%

    No Known Activations