© 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. 5-CLT-HP
    7. 98279
    Prev
    Next
    INDEX
    Explanations

    scientific measurements

    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
    leqq
    -0.52
     estekak
    -0.52
    FormTagHelper
    -0.50
     Sodom
    -0.49
    Carrière
    -0.47
     otaku
    -0.46
     uploaded
    -0.46
     whir
    -0.46
     chameleon
    -0.44
     åt
    -0.44
    POSITIVE LOGITS
    g
    0.77
     absolute
    0.67
    abs
    0.64
    absolute
    0.61
     abs
    0.61
    G
    0.60
    }());
    0.59
    Absolute
    0.59
     absolue
    0.59
     g
    0.58
    Activations Density 0.001%

    No Known Activations