© 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. 0-CLT-HP
    7. 93244
    Prev
    Next
    INDEX
    Explanations

    results and implications

    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
     severe
    -0.94
     sauvages
    -0.90
     vectorielles
    -0.88
     quelcon
    -0.85
     sólidos
    -0.82
     complètes
    -0.82
     acute
    -0.81
     gezet
    -0.81
    severe
    -0.81
     généraux
    -0.81
    POSITIVE LOGITS
    ParallelGroup
    0.57
    ConstraintMaker
    0.56
     initComponents
    0.50
     oj
    0.49
     roboc
    0.47
     indestru
    0.46
     inn
    0.45
     atta
    0.44
    cfm
    0.44
     pieces
    0.43
    Activations Density 0.046%

    No Known Activations