© 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. 1-CLT-HP
    7. 15620
    Prev
    Next
    INDEX
    Explanations

    printers, HPV, CNC

    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
    ChildScrollView
    -0.72
    kloped
    -0.67
    styleType
    -0.63
     OnInit
    -0.54
     Paglinawan
    -0.52
    +#+
    -0.51
    hoeddwyd
    -0.51
    printer
    -0.51
    Personendaten
    -0.50
     resourceCulture
    -0.50
    POSITIVE LOGITS
     Ver
    0.59
    ClassId
    0.58
    ンダント
    0.52
     clubhouse
    0.51
     fermions
    0.51
    liosis
    0.50
     Theodo
    0.50
     Latch
    0.50
     Lanz
    0.50
     Smoke
    0.50
    Activations Density 0.048%

    No Known Activations