© 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. 20-CLT-HP
    7. 76487
    Prev
    Next
    INDEX
    Explanations

    Ca

    np_max-act-logits · 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
    المصادر
    -0.57
     Walkover
    -0.56
     saites
    -0.55
    oa̍t
    -0.54
     bezeichneter
    -0.54
    ImageField
    -0.52
     handleMessage
    -0.51
     Waray
    -0.50
    prepareStatement
    -0.50
     ligiloj
    -0.49
    POSITIVE LOGITS
     OFDb
    0.51
     bicchiere
    0.51
     Wheels
    0.50
     متعلقه
    0.50
     lccn
    0.50
    锈钢
    0.49
    esac
    0.49
    using
    0.49
    лябин
    0.48
     wheels
    0.47
    Activations Density 0.002%

    No Known Activations