© 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. 1-CLT-HP
    7. 14464
    Prev
    Next
    INDEX
    Explanations

    of

    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
     many
    -0.76
     leçons
    -0.73
     niekoľ
    -0.72
     bénévoles
    -0.70
    many
    -0.70
     néhány
    -0.69
     många
    -0.69
     mnoho
    -0.69
     Many
    -0.69
    Numerous
    -0.68
    POSITIVE LOGITS
     respects
    0.57
    TagHelpers
    0.56
    InvalidProtocol
    0.55
     instruments
    0.54
     parameters
    0.54
     symptoms
    0.53
     scales
    0.53
     conditions
    0.53
     them
    0.51
     agents
    0.51
    Activations Density 0.033%

    No Known Activations