© 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. 4298
    Prev
    Next
    INDEX
    Explanations

    the

    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
     itſelf
    -0.67
     doubtnut
    -0.60
     Efq
    -0.55
     myſelf
    -0.53
     Cæsar
    -0.51
     elevators
    -0.51
     uſed
    -0.50
     ſtate
    -0.49
     Antara
    -0.49
     Monfieur
    -0.48
    POSITIVE LOGITS
    ↵↵
    0.64
    rungsseite
    0.60
     насељу
    0.59
    awtextra
    0.59
    FormTagHelper
    0.59
     initComponents
    0.59
    tagHelperRunner
    0.59
    DataPropertyName
    0.56
    MessageState
    0.56
    CloseOperation
    0.56
    Activations Density 0.003%

    No Known Activations