© 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. 3809
    Prev
    Next
    INDEX
    Explanations

    date

    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
     the
    -0.56
     non
    -0.55
     there
    -0.53
     return
    -0.50
     not
    -0.50
     G
    -0.49
     Carp
    -0.49
     face
    -0.49
     Su
    -0.48
    @[+][
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.84
    ValueStyle
    0.82
     imprimée
    0.73
     complètes
    0.70
     الحره
    0.70
    EndInit
    0.68
     dieux
    0.67
     suivie
    0.65
     sauvages
    0.65
    PerformLayout
    0.64
    Activations Density 0.001%

    No Known Activations