© 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. 4535
    Prev
    Next
    INDEX
    Explanations

    scientific/mechanical 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
     pinulongan
    -0.68
     vermogen
    -0.62
    opardy
    -0.54
    ulipas
    -0.53
     صوتيه
    -0.53
     vayas
    -0.53
     Arquivado
    -0.52
     nous
    -0.52
    getColumnIndex
    -0.51
    createTextNode
    -0.50
    POSITIVE LOGITS
     the
    1.02
     it
    0.69
    Bibliograf
    0.59
     down
    0.58
     their
    0.56
     up
    0.52
     things
    0.52
    GOTREF
    0.51
    enthe
    0.51
    RenderAtEndOf
    0.50
    Activations Density 0.001%

    No Known Activations