© 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. 97636
    Prev
    Next
    INDEX
    Explanations

    bravery, courage

    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
    Carcinogenicity
    -0.49
     stik
    -0.46
     retrouve
    -0.46
    GroupLayout
    -0.46
     Audiodateien
    -0.46
     Vasco
    -0.45
    unan
    -0.45
    downcase
    -0.44
     poitrine
    -0.44
    WebElementEntity
    -0.43
    POSITIVE LOGITS
     newOwner
    0.68
     архивлан
    0.57
    InjectAttribute
    0.55
     question
    0.55
     Nó
    0.53
    Халык
    0.53
     Bae
    0.53
    érale
    0.53
    intios
    0.53
    PerformLayout
    0.51
    Activations Density 0.002%

    No Known Activations