© 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. 92396
    Prev
    Next
    INDEX
    Explanations

    biological and chemical processes

    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
     مشين
    -0.69
    jalá
    -0.68
    AntiForgeryToken
    -0.65
    insee
    -0.63
     previa
    -0.58
     braços
    -0.57
     sekitarnya
    -0.57
    CodedInputStream
    -0.57
    άνει
    -0.57
    berdayakan
    -0.56
    POSITIVE LOGITS
     and
    0.60
     or
    0.52
    ⓧ
    0.48
     so
    0.43
    astify
    0.42
     akka
    0.41
     Visual
    0.41
     this
    0.41
    boer
    0.40
     visual
    0.40
    Activations Density 0.006%

    No Known Activations