© 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. 9074
    Prev
    Next
    INDEX
    Explanations

    placement

    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
     fumée
    -0.56
     stället
    -0.56
     jouets
    -0.55
     mauvaises
    -0.54
     riduzione
    -0.52
     passés
    -0.52
     kautta
    -0.50
     cromado
    -0.50
     éduc
    -0.50
     rapides
    -0.50
    POSITIVE LOGITS
     MainAxisSize
    0.71
    bibitem
    0.68
    Kapcsolódó
    0.65
    IANGLES
    0.65
    λέον
    0.63
     chi̍t
    0.61
     normal
    0.61
     orth
    0.61
    Pautan
    0.59
    testify
    0.58
    Activations Density 0.024%

    No Known Activations