© 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. 5-CLT-HP
    7. 5372
    Prev
    Next
    INDEX
    Explanations

    Place names

    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
     peggio
    -0.64
     zelve
    -0.63
     seguenti
    -0.59
     ragioni
    -0.56
    '));
    -0.56
     pouvoit
    -0.55
     zijne
    -0.54
     remercier
    -0.53
     suivants
    -0.52
     preghi
    -0.52
    POSITIVE LOGITS
     model
    0.76
     Centre
    0.76
     dealer
    0.75
     family
    0.74
     project
    0.73
     label
    0.73
     system
    0.72
     team
    0.71
     plant
    0.71
     Center
    0.70
    Activations Density 0.137%

    No Known Activations