© 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. 0-CLT-HP
    7. 40626
    Prev
    Next
    INDEX
    Explanations

    screws and mechanical errors

    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
    screw
    -0.59
    Screw
    -0.59
     Screw
    -0.58
     screw
    -0.58
    gate
    -0.57
     error
    -0.54
    routeProvider
    -0.50
     equivo
    -0.48
    airbnb
    -0.48
     дописавши
    -0.48
    POSITIVE LOGITS
    awtextra
    0.60
    cerely
    0.59
    ELSE
    0.58
    ieteur
    0.57
     linkovi
    0.57
     peep
    0.55
     bağlantılar
    0.55
    ázaro
    0.55
     ENO
    0.54
     thiệu
    0.54
    Activations Density 0.075%

    No Known Activations