© 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. 5-CLT-HP
    7. 97777
    Prev
    Next
    INDEX
    Explanations

    biographies

    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
    checs
    -0.46
     LoginComponent
    -0.44
     répé
    -0.44
    illir
    -0.44
     meia
    -0.43
    ferde
    -0.43
    averaged
    -0.42
     Erwachsene
    -0.42
     niên
    -0.42
     képes
    -0.41
    POSITIVE LOGITS
     مشين
    0.69
    DockStyle
    0.68
     passim
    0.61
    MessageTagHelper
    0.61
    onedDateTime
    0.60
     Biôgrafia
    0.59
    OrBuilder
    0.58
    RenderAtEndOf
    0.57
    FormTagHelper
    0.57
     arriving
    0.56
    Activations Density 0.017%

    No Known Activations