© 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. 5317
    Prev
    Next
    INDEX
    Explanations

    lists

    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
    WriteTagHelper
    -0.45
    felt
    -0.45
    ILAR
    -0.44
    understood
    -0.43
    معلومات
    -0.43
    fixes
    -0.42
    DataMember
    -0.42
    tagHelper
    -0.42
    gete
    -0.41
    MessageOf
    -0.41
    POSITIVE LOGITS
     Yel
    0.73
    complexContent
    0.73
     pngtree
    0.65
     cdti
    0.65
     يتيمه
    0.64
     Negroes
    0.62
     ſind
    0.62
     myſelf
    0.62
     Mosca
    0.60
     Luci
    0.60
    Activations Density 0.004%

    No Known Activations