© 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. 0-CLT-HP
    7. 43268
    Prev
    Next
    INDEX
    Explanations

    academic research

    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
    ing
    -0.71
    hesive
    -0.69
    ness
    -0.57
    hesion
    -0.56
     Article
    -0.50
    es
    -0.47
    n
    -0.46
    esine
    -0.44
    s
    -0.44
    ny
    -0.43
    POSITIVE LOGITS
     initComponents
    0.89
     насељу
    0.83
     Audiodateien
    0.82
    ChildScrollView
    0.82
    principalColumn
    0.82
    sizeCache
    0.75
    oneph
    0.75
     BoxDecoration
    0.75
    новништво
    0.74
     محفوظة
    0.74
    Activations Density 1.544%

    No Known Activations