© 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. 1-CLT-HP
    7. 10838
    Prev
    Next
    INDEX
    Explanations

    thinking

    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
    protoimpl
    -0.71
     betweenstory
    -0.68
     viewDidLoad
    -0.67
    COUVER
    -0.66
     חיצוניים
    -0.65
    évaluateur
    -0.65
     dévelo
    -0.64
    Дереккөздер
    -0.64
     мәкал
    -0.64
    دانشنامهٔ
    -0.63
    POSITIVE LOGITS
    setVerticalGroup
    0.61
    contentLoaded
    0.44
    ökning
    0.42
    toggler
    0.41
     Italiana
    0.40
    TagMode
    0.40
    localctx
    0.39
    zarchiwizowane
    0.38
    sortable
    0.37
     TRANSL
    0.36
    Activations Density 0.002%

    No Known Activations