© 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. 0-CLT-HP
    7. 92913
    Prev
    Next
    INDEX
    Explanations

    flourished

    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
     Proving
    -0.63
    EUROPA
    -0.57
     '{@
    -0.57
     downvotes
    -0.54
     Neolithic
    -0.54
     overlying
    -0.53
     Phoen
    -0.53
     Mercier
    -0.52
    atin
    -0.52
    TestBed
    -0.52
    POSITIVE LOGITS
    protoimpl
    0.71
     تضيفلها
    0.68
    verages
    0.65
    rungsseite
    0.63
    heets
    0.60
     للاسماء
    0.57
     للمعارف
    0.54
    __*/
    0.54
    mények
    0.53
    sheets
    0.52
    Activations Density 0.224%

    No Known Activations