© 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. 1-CLT-HP
    7. 13798
    Prev
    Next
    INDEX
    Explanations

    Thi

    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
     Thi
    -0.88
    Thi
    -0.85
     églises
    -0.57
     thi
    -0.55
    WithIdentifier
    -0.55
    URLEncoder
    -0.52
     enjeux
    -0.52
     död
    -0.50
    umab
    -0.50
    IsPostBack
    -0.49
    POSITIVE LOGITS
    "}"
    0.58
     counting
    0.56
    Bronnen
    0.55
    Bureau
    0.54
    ंदीखरीदारी
    0.53
    protoimpl
    0.52
     counts
    0.52
     Bureau
    0.52
    IsMutable
    0.51
    elfs
    0.50
    Activations Density 0.010%

    No Known Activations