© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1456
    Prev
    Next
    INDEX
    Explanations

    start and end

    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
    oredCriteria
    -0.53
    IUrlHelper
    -0.52
    SuppressLint
    -0.51
    Pautan
    -0.50
    stdc
    -0.50
     Ubicación
    -0.46
     strepto
    -0.45
     survie
    -0.45
     refusé
    -0.44
     affirmé
    -0.44
    POSITIVE LOGITS
    VersionUID
    0.84
     protoimpl
    0.66
    المشاركات
    0.61
     AssemblyCompany
    0.58
    horesis
    0.57
    ]--;
    0.57
     الحره
    0.57
    TagMode
    0.56
    WriteTagHelper
    0.56
    таратура
    0.55
    Activations Density 0.013%

    No Known Activations