© 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. 41245
    Prev
    Next
    INDEX
    Explanations

    corrected/containing

    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
     correct
    -1.30
    correct
    -1.30
     Correct
    -1.10
    Correct
    -1.05
     correcta
    -1.00
     corrected
    -0.99
     corrects
    -0.96
     CORRECT
    -0.89
     correctness
    -0.88
     correta
    -0.87
    POSITIVE LOGITS
     heme
    0.59
    itoneal
    0.52
     Metabol
    0.50
     glands
    0.50
    itoneum
    0.49
     amino
    0.49
     phosphate
    0.49
     contextLoads
    0.49
     aromatic
    0.48
     dye
    0.47
    Activations Density 0.205%

    No Known Activations