© 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. 14913
    Prev
    Next
    INDEX
    Explanations

    apostrophe

    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
     '
    -1.16
     ‘
    -1.16
    ‘
    -0.90
    『
    -0.73
     (‘
    -0.72
     ('
    -0.63
    '
    -0.60
     pauvres
    -0.60
     ';
    -0.59
    ,'
    -0.58
    POSITIVE LOGITS
    ViewFeatures
    0.85
    ValueGenerated
    0.73
    новништво
    0.65
     snippetHide
    0.64
     متعلقه
    0.61
    fjspx
    0.60
     <>",
    0.60
    TagHelpers
    0.60
    IsContent
    0.59
     <=",
    0.59
    Activations Density 1.113%

    No Known Activations