© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 620
    Prev
    Next
    INDEX
    Explanations

    that

    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
     étoit
    -0.75
     propOrder
    -0.74
     lasts
    -0.71
     avviene
    -0.71
     enfans
    -0.71
     awaits
    -0.69
     Administrativna
    -0.67
    ussis
    -0.67
     auroit
    -0.67
     exceeds
    -0.65
    POSITIVE LOGITS
     have
    0.86
     emerge
    0.68
    have
    0.67
     arise
    0.65
     appear
    0.61
     exist
    0.60
     define
    0.60
     continue
    0.57
     determine
    0.56
    were
    0.56
    Activations Density 0.006%

    No Known Activations