© 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. 1-CLT-HP
    7. 9065
    Prev
    Next
    INDEX
    Explanations

    its

    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
    ValueStyle
    -0.74
    ContentAsync
    -0.73
     volgt
    -0.68
     chré
    -0.67
     préc
    -0.65
     charité
    -0.64
     réforme
    -0.64
     defaultstate
    -0.61
    IntoConstraints
    -0.60
     rempliss
    -0.60
    POSITIVE LOGITS
     own
    0.69
     role
    0.61
     main
    0.60
     primary
    0.59
     traditional
    0.56
     usual
    0.56
     الحره
    0.54
     yard
    0.54
     service
    0.53
     entire
    0.53
    Activations Density 0.011%

    No Known Activations