© 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. 5-CLT-HP
    7. 3596
    Prev
    Next
    INDEX
    Explanations

    mechanical/electrical systems

    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
      (
    -0.47
    ModelForm
    -0.44
     feu
    -0.44
     hubiera
    -0.42
    ിച്ച
    -0.41
    atellite
    -0.40
    Traduction
    -0.40
     compter
    -0.39
    );\
    -0.39
    into
    -0.39
    POSITIVE LOGITS
     חיצוניים
    0.70
    contentLoaded
    0.66
    OpenHelper
    0.64
    featureID
    0.63
    Personendaten
    0.61
     of
    0.61
     BoxDecoration
    0.59
    gdala
    0.57
     ब्रेकडाउन
    0.56
    webElementXpaths
    0.55
    Activations Density 0.003%

    No Known Activations